diff --git a/.github/workflows/deploy-docs-site.yaml b/.github/workflows/deploy-docs-site.yaml index b1785292..d3fee6cb 100644 --- a/.github/workflows/deploy-docs-site.yaml +++ b/.github/workflows/deploy-docs-site.yaml @@ -4,7 +4,6 @@ on: push: branches: - main - - docs-site-poc paths: - ".github/workflows/deploy-docs-site.yaml" - "docs/**" @@ -45,9 +44,7 @@ jobs: - name: Deploy uses: peaceiris/actions-gh-pages@v3 - if: - ${{ github.ref == 'refs/heads/main' || github.ref == - 'refs/heads/docs-site-poc' }} + if: ${{ github.ref == 'refs/heads/main' }} with: github_token: ${{ secrets.GITHUB_TOKEN }} publish_dir: ./docs/build diff --git a/CODEOWNERS b/CODEOWNERS index c5cc1467..f1eb32de 100644 --- a/CODEOWNERS +++ b/CODEOWNERS @@ -2,3 +2,5 @@ /website/ @fozziethebeat @k-nearest-neighbor @AbdBarho /model/ @theblackcat102 @sanagno /copilot/ @fozziethebeat @andreaskoepf @yk +/docs/ @andrewm4894 @andreaskoepf @yk +/.devcontainer/ @andrewm4894 @andreaskoepf @yk diff --git a/README.md b/README.md index e6a682ec..7cac0788 100644 --- a/README.md +++ b/README.md @@ -6,6 +6,7 @@
![GitHub Repo stars](https://img.shields.io/github/stars/LAION-AI/Open-Assistant?style=social) +![Docs](https://img.shields.io/badge/docs-laion--ai.github.io%2FOpen--Assistant%2F-green) ![GitHub Workflow Status](https://img.shields.io/github/actions/workflow/status/LAION-AI/Open-Assistant/build-frontend.yaml?label=frontend) ![GitHub Workflow Status](https://img.shields.io/github/actions/workflow/status/LAION-AI/Open-Assistant/pre-commit.yaml?label=pre-commit) ![GitHub Workflow Status](https://img.shields.io/github/actions/workflow/status/LAION-AI/Open-Assistant/test-api-contract.yaml?label=api) diff --git a/backend/README.md b/backend/README.md index 863090f7..a9507d5e 100644 --- a/backend/README.md +++ b/backend/README.md @@ -1,5 +1,18 @@ # Open-Assistant REST Backend +## Backend Development Setup + +In root directory, run +`docker compose up backend-dev --build --attach-dependencies` to start a +database. The default settings are already configured to connect to the database +at `localhost:5432`. + +Make sure you have all requirements installed. You can do this by running +`pip install -r requirements.txt` inside the `backend` folder and +`pip install -e .` inside the `oasst-shared` folder. Then, run the backend using +the `run-local.sh` script inside the `scripts` folder. This will start the +backend server at `http://localhost:8080`. + ## REST Server Configuration Please either use environment variables or create a `.env` file in the backend @@ -20,3 +33,11 @@ REDIS_PORT=6379 Have a look into the main `README.md` file for more information on how to set up the backend for development. Use the scripts within the scripts/backend-development folder to run the BE API locally. + +## Alembic + +To create an Alembic database migration script after sql-models were modified +run `alembic revision --autogenerate -m "..."` ("..." is what you did) in the +`/backend` directory. Then edit the newly created file. See +[here](https://alembic.sqlalchemy.org/en/latest/tutorial.html) for more +information. diff --git a/backend/alembic/versions/2023_01_07_1250-ba61fe17fb6e_added_frontend_type_to_api_client.py b/backend/alembic/versions/2023_01_07_1250-ba61fe17fb6e_added_frontend_type_to_api_client.py new file mode 100644 index 00000000..dbc89ebf --- /dev/null +++ b/backend/alembic/versions/2023_01_07_1250-ba61fe17fb6e_added_frontend_type_to_api_client.py @@ -0,0 +1,23 @@ +"""added frontend_type to api_client + +Revision ID: ba61fe17fb6e +Revises: 20cd871f4ec7 +Create Date: 2023-01-07 12:50:32.195930 + +""" +import sqlalchemy as sa +from alembic import op + +# revision identifiers, used by Alembic. +revision = "ba61fe17fb6e" +down_revision = "20cd871f4ec7" +branch_labels = None +depends_on = None + + +def upgrade() -> None: + op.add_column("api_client", sa.Column("frontend_type", sa.String(256), nullable=True)) + + +def downgrade() -> None: + op.drop_column("api_client", "frontend_id") diff --git a/backend/main.py b/backend/main.py index edbad943..1c93fc9f 100644 --- a/backend/main.py +++ b/backend/main.py @@ -1,3 +1,4 @@ +import json from http import HTTPStatus from math import ceil from pathlib import Path @@ -6,7 +7,6 @@ from typing import Optional import alembic.command import alembic.config import fastapi -import pydantic import redis.asyncio as redis from fastapi_limiter import FastAPILimiter from loguru import logger @@ -17,6 +17,7 @@ from oasst_backend.database import engine from oasst_backend.prompt_repository import PromptRepository from oasst_shared.exceptions import OasstError, OasstErrorCode from oasst_shared.schemas import protocol as protocol_schema +from pydantic import BaseModel from sqlmodel import Session from starlette.middleware.cors import CORSMiddleware @@ -97,7 +98,7 @@ if settings.DEBUG_USE_SEED_DATA: @app.on_event("startup") def seed_data(): - class DummyMessage(pydantic.BaseModel): + class DummyMessage(BaseModel): task_message_id: str user_message_id: str parent_message_id: Optional[str] @@ -111,64 +112,10 @@ if settings.DEBUG_USE_SEED_DATA: dummy_user = protocol_schema.User(id="__dummy_user__", display_name="Dummy User", auth_method="local") pr = PromptRepository(db=db, api_client=api_client, user=dummy_user) - dummy_messages = [ - DummyMessage( - task_message_id="de111fa8", - user_message_id="6f1d0711", - parent_message_id=None, - text="Hi!", - role="prompter", - ), - DummyMessage( - task_message_id="74c381d4", - user_message_id="4a24530b", - parent_message_id="6f1d0711", - text="Hello! How can I help you?", - role="assistant", - ), - DummyMessage( - task_message_id="3d5dc440", - user_message_id="a8c01c04", - parent_message_id="4a24530b", - text="Do you have a recipe for potato soup?", - role="prompter", - ), - DummyMessage( - task_message_id="643716c1", - user_message_id="f43a93b7", - parent_message_id="4a24530b", - text="Who were the 8 presidents before George Washington?", - role="prompter", - ), - DummyMessage( - task_message_id="2e4e1e6", - user_message_id="c886920", - parent_message_id="6f1d0711", - text="Hey buddy! How can I serve you?", - role="assistant", - ), - DummyMessage( - task_message_id="970c437d", - user_message_id="cec432cf", - parent_message_id=None, - text="euirdteunvglfe23908230892309832098 AAAAAAAA", - role="prompter", - ), - DummyMessage( - task_message_id="6066118e", - user_message_id="4f85f637", - parent_message_id="cec432cf", - text="Sorry, I did not understand your request and it is unclear to me what you want me to do. Could you describe it in a different way?", - role="assistant", - ), - DummyMessage( - task_message_id="ba87780d", - user_message_id="0e276b98", - parent_message_id="cec432cf", - text="I'm unsure how to interpret this. Is it a riddle?", - role="assistant", - ), - ] + with open(settings.DEBUG_USE_SEED_DATA_PATH) as f: + dummy_messages_raw = json.load(f) + + dummy_messages = [DummyMessage(**dm) for dm in dummy_messages_raw] for msg in dummy_messages: task = pr.fetch_task_by_frontend_message_id(msg.task_message_id) @@ -185,12 +132,20 @@ if settings.DEBUG_USE_SEED_DATA: parent_message = pr.fetch_message_by_frontend_message_id( msg.parent_message_id, fail_if_missing=True ) - task = pr.store_task( - protocol_schema.AssistantReplyTask( - conversation=protocol_schema.Conversation( - messages=[protocol_schema.ConversationMessage(text="dummy", is_assistant=False)] + conversation_messages = pr.fetch_message_conversation(parent_message) + conversation = protocol_schema.Conversation( + messages=[ + protocol_schema.ConversationMessage( + text=cmsg.text, + is_assistant=cmsg.role == "assistant", + message_id=cmsg.id, + fronend_message_id=cmsg.frontend_message_id, ) - ), + for cmsg in conversation_messages + ] + ) + task = pr.store_task( + protocol_schema.AssistantReplyTask(conversation=conversation), message_tree_id=parent_message.message_tree_id, parent_message_id=parent_message.id, ) @@ -219,7 +174,6 @@ if __name__ == "__main__": # Importing here so we don't import packages unnecessarily if we're # importing main as a module. import argparse - import json import uvicorn diff --git a/backend/oasst_backend/api/deps.py b/backend/oasst_backend/api/deps.py index f61947cd..901ec8ab 100644 --- a/backend/oasst_backend/api/deps.py +++ b/backend/oasst_backend/api/deps.py @@ -40,7 +40,13 @@ def get_dummy_api_client(db: Session) -> ApiClient: if api_client is None: token = token_hex(32) logger.info(f"ANY_API_KEY missing, inserting api_key: {token}") - api_client = ApiClient(id=ANY_API_KEY_ID, api_key=token, description="ANY_API_KEY, random token", trusted=True) + api_client = ApiClient( + id=ANY_API_KEY_ID, + api_key=token, + description="ANY_API_KEY, random token", + trusted=True, + frontend_type="Test frontend", + ) db.add(api_client) db.commit() return api_client diff --git a/backend/oasst_backend/api/v1/frontend_messages.py b/backend/oasst_backend/api/v1/frontend_messages.py index 956d9992..420f0d1b 100644 --- a/backend/oasst_backend/api/v1/frontend_messages.py +++ b/backend/oasst_backend/api/v1/frontend_messages.py @@ -2,9 +2,7 @@ from fastapi import APIRouter, Depends from oasst_backend.api import deps from oasst_backend.api.v1 import utils from oasst_backend.models import ApiClient -from oasst_backend.models.db_payload import MessagePayload from oasst_backend.prompt_repository import PromptRepository -from oasst_shared.exceptions import OasstError, OasstErrorCode from oasst_shared.schemas import protocol from sqlmodel import Session @@ -20,11 +18,6 @@ def get_message_by_frontend_id( """ pr = PromptRepository(db, api_client, user=None) message = pr.fetch_message_by_frontend_message_id(message_id) - - if not isinstance(message.payload.payload, MessagePayload): - # Unexpected message payload - raise OasstError("Invalid message", OasstErrorCode.INVALID_MESSAGE) - return utils.prepare_message(message) diff --git a/backend/oasst_backend/api/v1/messages.py b/backend/oasst_backend/api/v1/messages.py index 951355b3..7a2fd2e9 100644 --- a/backend/oasst_backend/api/v1/messages.py +++ b/backend/oasst_backend/api/v1/messages.py @@ -5,9 +5,7 @@ from fastapi import APIRouter, Depends, Query from oasst_backend.api import deps from oasst_backend.api.v1 import utils from oasst_backend.models import ApiClient -from oasst_backend.models.db_payload import MessagePayload from oasst_backend.prompt_repository import PromptRepository -from oasst_shared.exceptions import OasstError, OasstErrorCode from oasst_shared.schemas import protocol from sqlmodel import Session from starlette.status import HTTP_204_NO_CONTENT @@ -55,10 +53,6 @@ def get_message( """ pr = PromptRepository(db, api_client, user=None) message = pr.fetch_message(message_id) - if not isinstance(message.payload.payload, MessagePayload): - # Unexptcted message payload - raise OasstError("Invalid message", OasstErrorCode.INVALID_MESSAGE) - return utils.prepare_message(message) diff --git a/backend/oasst_backend/api/v1/tasks.py b/backend/oasst_backend/api/v1/tasks.py index 9f81eabb..adfb2907 100644 --- a/backend/oasst_backend/api/v1/tasks.py +++ b/backend/oasst_backend/api/v1/tasks.py @@ -6,6 +6,7 @@ from fastapi import APIRouter, Depends from fastapi.security.api_key import APIKey from loguru import logger from oasst_backend.api import deps +from oasst_backend.api.v1.utils import prepare_conversation from oasst_backend.prompt_repository import PromptRepository from oasst_shared.exceptions import OasstError, OasstErrorCode from oasst_shared.schemas import protocol as protocol_schema @@ -58,7 +59,10 @@ def generate_task( messages = pr.fetch_random_conversation("assistant") task_messages = [ protocol_schema.ConversationMessage( - text=msg.payload.payload.text, is_assistant=(msg.role == "assistant") + text=msg.text, + is_assistant=(msg.role == "assistant"), + message_id=msg.id, + front_end_id=msg.frontend_message_id, ) for msg in messages ] @@ -71,7 +75,10 @@ def generate_task( messages = pr.fetch_random_conversation("prompter") task_messages = [ protocol_schema.ConversationMessage( - text=msg.payload.payload.text, is_assistant=(msg.role == "assistant") + text=msg.text, + is_assistant=(msg.role == "assistant"), + message_id=msg.id, + front_end_id=msg.frontend_message_id, ) for msg in messages ] @@ -83,19 +90,21 @@ def generate_task( logger.info("Generating a RankInitialPromptsTask.") messages = pr.fetch_random_initial_prompts() - task = protocol_schema.RankInitialPromptsTask(prompts=[msg.payload.payload.text for msg in messages]) + task = protocol_schema.RankInitialPromptsTask(prompts=[msg.text for msg in messages]) case protocol_schema.TaskRequestType.rank_prompter_replies: logger.info("Generating a RankPrompterRepliesTask.") conversation, replies = pr.fetch_multiple_random_replies(message_role="assistant") task_messages = [ protocol_schema.ConversationMessage( - text=p.payload.payload.text, + text=p.text, is_assistant=(p.role == "assistant"), + message_id=p.id, + front_end_id=p.frontend_message_id, ) for p in conversation ] - replies = [p.payload.payload.text for p in replies] + replies = [p.text for p in replies] task = protocol_schema.RankPrompterRepliesTask( conversation=protocol_schema.Conversation( messages=task_messages, @@ -109,14 +118,16 @@ def generate_task( task_messages = [ protocol_schema.ConversationMessage( - text=p.payload.payload.text, + text=p.text, is_assistant=(p.role == "assistant"), + message_id=p.id, + front_end_id=p.frontend_message_id, ) for p in conversation ] - replies = [p.payload.payload.text for p in replies] + replies = [p.text for p in replies] task = protocol_schema.RankAssistantRepliesTask( - conversation=protocol_schema.Conversation(messages=task_messages), + conversation=prepare_conversation(conversation), replies=replies, ) @@ -125,29 +136,29 @@ def generate_task( message = pr.fetch_random_initial_prompts(1)[0] task = protocol_schema.LabelInitialPromptTask( message_id=message.id, - prompt=message.payload.payload.text, + prompt=message.text, valid_labels=list(map(lambda x: x.value, protocol_schema.TextLabel)), ) case protocol_schema.TaskRequestType.label_prompter_reply: logger.info("Generating a LabelPrompterReplyTask.") conversation, messages = pr.fetch_multiple_random_replies(max_size=1, message_role="assistant") - message = messages[0].payload.payload.text + message = messages[0] task = protocol_schema.LabelPrompterReplyTask( message_id=message.id, - conversation=conversation, - reply=message, + conversation=prepare_conversation(conversation), + reply=message.text, valid_labels=list(map(lambda x: x.value, protocol_schema.TextLabel)), ) case protocol_schema.TaskRequestType.label_assistant_reply: logger.info("Generating a LabelAssistantReplyTask.") conversation, messages = pr.fetch_multiple_random_replies(max_size=1, message_role="prompter") - message = messages[0].payload.payload.text + message = messages[0] task = protocol_schema.LabelAssistantReplyTask( message_id=message.id, - conversation=conversation, - reply=message, + conversation=prepare_conversation(conversation), + reply=message.text, valid_labels=list(map(lambda x: x.value, protocol_schema.TextLabel)), ) @@ -292,7 +303,8 @@ def tasks_interaction( logger.info( f"Frontend reports labels of {interaction.message_id=} with {interaction.labels=} by {interaction.user=}." ) - # TODO: check if the labels are valid? + # Labels are implicitly validated when converting str -> TextLabel + # So no need for explicit validation here pr.store_text_labels(interaction) return protocol_schema.TaskDone() case _: diff --git a/backend/oasst_backend/api/v1/text_labels.py b/backend/oasst_backend/api/v1/text_labels.py index 97422119..03fd2cb4 100644 --- a/backend/oasst_backend/api/v1/text_labels.py +++ b/backend/oasst_backend/api/v1/text_labels.py @@ -3,6 +3,7 @@ from fastapi.security.api_key import APIKey from loguru import logger from oasst_backend.api import deps from oasst_backend.prompt_repository import PromptRepository +from oasst_backend.schemas.text_labels import LabelOption, ValidLabelsResponse from oasst_shared.schemas import protocol as protocol_schema from sqlmodel import Session from starlette.status import HTTP_204_NO_CONTENT, HTTP_400_BAD_REQUEST @@ -32,3 +33,13 @@ def label_text( raise HTTPException( status_code=HTTP_400_BAD_REQUEST, ) + + +@router.get("/valid_labels") +def get_valid_lables() -> ValidLabelsResponse: + return ValidLabelsResponse( + valid_labels=[ + LabelOption(name=l.value, display_text=l.display_text, help_text=l.help_text) + for l in protocol_schema.TextLabel + ] + ) diff --git a/backend/oasst_backend/api/v1/utils.py b/backend/oasst_backend/api/v1/utils.py index 55a7c572..4e20395f 100644 --- a/backend/oasst_backend/api/v1/utils.py +++ b/backend/oasst_backend/api/v1/utils.py @@ -1,19 +1,14 @@ -from http import HTTPStatus from uuid import UUID from oasst_backend.models import Message -from oasst_backend.models.db_payload import MessagePayload -from oasst_shared.exceptions import OasstError, OasstErrorCode from oasst_shared.schemas import protocol def prepare_message(m: Message) -> protocol.Message: - if not isinstance(m.payload.payload, MessagePayload): - raise OasstError("Server error", OasstErrorCode.SERVER_ERROR, HTTPStatus.INTERNAL_SERVER_ERROR) return protocol.Message( id=m.id, parent_id=m.parent_id, - text=m.payload.payload.text, + text=m.text, is_assistant=(m.role == "assistant"), created_date=m.created_date, ) @@ -26,10 +21,13 @@ def prepare_message_list(messages: list[Message]) -> list[protocol.Message]: def prepare_conversation(messages: list[Message]) -> protocol.Conversation: conv_messages = [] for message in messages: - if not isinstance(message.payload.payload, MessagePayload): - raise OasstError("Server error", OasstErrorCode.SERVER_ERROR, HTTPStatus.INTERNAL_SERVER_ERROR) conv_messages.append( - protocol.ConversationMessage(text=message.payload.payload.text, is_assistant=(message.role == "assistant")) + protocol.ConversationMessage( + text=message.text, + is_assistant=(message.role == "assistant"), + message_id=message.id, + frontend_message_id=message.frontend_message_id, + ) ) return protocol.Conversation(messages=conv_messages) @@ -38,8 +36,6 @@ def prepare_conversation(messages: list[Message]) -> protocol.Conversation: def prepare_tree(tree: list[Message], tree_id: UUID) -> protocol.MessageTree: tree_messages = [] for message in tree: - if not isinstance(message.payload.payload, MessagePayload): - raise OasstError("Server error", OasstErrorCode.SERVER_ERROR, HTTPStatus.INTERNAL_SERVER_ERROR) tree_messages.append(prepare_message(message)) return protocol.MessageTree(id=tree_id, messages=tree_messages) diff --git a/backend/oasst_backend/config.py b/backend/oasst_backend/config.py index df37dc9f..1765af7a 100644 --- a/backend/oasst_backend/config.py +++ b/backend/oasst_backend/config.py @@ -1,6 +1,7 @@ +from pathlib import Path from typing import Any, Dict, List, Optional, Union -from pydantic import AnyHttpUrl, BaseSettings, PostgresDsn, validator +from pydantic import AnyHttpUrl, BaseSettings, FilePath, PostgresDsn, validator class Settings(BaseSettings): @@ -21,6 +22,9 @@ class Settings(BaseSettings): DEBUG_ALLOW_ANY_API_KEY: bool = False DEBUG_SKIP_API_KEY_CHECK: bool = False DEBUG_USE_SEED_DATA: bool = False + DEBUG_USE_SEED_DATA_PATH: Optional[FilePath] = ( + Path(__file__).parent.parent / "test_data/generic/test_generic_data.json" + ) HUGGING_FACE_API_KEY: str = "" diff --git a/backend/oasst_backend/models/api_client.py b/backend/oasst_backend/models/api_client.py index 0bebec47..9b8f2aaa 100644 --- a/backend/oasst_backend/models/api_client.py +++ b/backend/oasst_backend/models/api_client.py @@ -20,3 +20,4 @@ class ApiClient(SQLModel, table=True): admin_email: Optional[str] = Field(max_length=256, nullable=True) enabled: bool = Field(default=True) trusted: bool = Field(sa_column=sa.Column(sa.Boolean, nullable=False, server_default=false())) + frontend_type: str = Field(max_length=256, nullable=True) diff --git a/backend/oasst_backend/models/journal.py b/backend/oasst_backend/models/journal.py index 0d5a78af..b5000add 100644 --- a/backend/oasst_backend/models/journal.py +++ b/backend/oasst_backend/models/journal.py @@ -32,7 +32,7 @@ class Journal(SQLModel, table=True): created_date: Optional[datetime] = Field( sa_column=sa.Column(sa.DateTime(timezone=True), nullable=False, server_default=sa.func.current_timestamp()) ) - user_id: UUID = Field(nullable=True, foreign_key="user.id", index=True) + user_id: Optional[UUID] = Field(nullable=True, foreign_key="user.id", index=True) message_id: Optional[UUID] = Field(foreign_key="message.id", nullable=True) api_client_id: UUID = Field(foreign_key="api_client.id") @@ -49,7 +49,7 @@ class JournalIntegration(SQLModel, table=True): ), ) description: str = Field(max_length=512, primary_key=True) - last_journal_id: UUID = Field(foreign_key="journal.id", nullable=True) - last_run: datetime = Field(sa_column=sa.Column(sa.DateTime(), nullable=True)) - last_error: str = Field(nullable=True) - next_run: datetime = Field(nullable=True) + last_journal_id: Optional[UUID] = Field(foreign_key="journal.id", nullable=True) + last_run: Optional[datetime] = Field(sa_column=sa.Column(sa.DateTime(), nullable=True)) + last_error: Optional[str] = Field(nullable=True) + next_run: Optional[datetime] = Field(nullable=True) diff --git a/backend/oasst_backend/models/message.py b/backend/oasst_backend/models/message.py index f07ca881..6d24fd13 100644 --- a/backend/oasst_backend/models/message.py +++ b/backend/oasst_backend/models/message.py @@ -1,9 +1,12 @@ from datetime import datetime +from http import HTTPStatus from typing import Optional from uuid import UUID, uuid4 import sqlalchemy as sa import sqlalchemy.dialects.postgresql as pg +from oasst_backend.models.db_payload import MessagePayload +from oasst_shared.exceptions.oasst_api_error import OasstError, OasstErrorCode from sqlalchemy import false from sqlmodel import Field, Index, SQLModel @@ -19,19 +22,30 @@ class Message(SQLModel, table=True): pg.UUID(as_uuid=True), primary_key=True, default=uuid4, server_default=sa.text("gen_random_uuid()") ), ) - parent_id: UUID = Field(nullable=True) + parent_id: Optional[UUID] = Field(nullable=True) message_tree_id: UUID = Field(nullable=False, index=True) - task_id: UUID = Field(nullable=True, index=True) - user_id: UUID = Field(nullable=True, foreign_key="user.id", index=True) - role: str = Field(nullable=False, max_length=128) # valid: "prompter" | "assistant" + task_id: Optional[UUID] = Field(nullable=True, index=True) + user_id: Optional[UUID] = Field(nullable=True, foreign_key="user.id", index=True) + role: str = Field(nullable=False, max_length=128, regex="^prompter|assistant$") api_client_id: UUID = Field(nullable=False, foreign_key="api_client.id") frontend_message_id: str = Field(max_length=200, nullable=False) created_date: Optional[datetime] = Field( sa_column=sa.Column(sa.DateTime(), nullable=False, server_default=sa.func.current_timestamp()) ) payload_type: str = Field(nullable=False, max_length=200) - payload: PayloadContainer = Field(sa_column=sa.Column(payload_column_type(PayloadContainer), nullable=True)) + payload: Optional[PayloadContainer] = Field( + sa_column=sa.Column(payload_column_type(PayloadContainer), nullable=True) + ) lang: str = Field(nullable=False, max_length=200, default="en-US") depth: int = Field(sa_column=sa.Column(sa.Integer, default=0, server_default=sa.text("0"), nullable=False)) children_count: int = Field(sa_column=sa.Column(sa.Integer, default=0, server_default=sa.text("0"), nullable=False)) deleted: bool = Field(sa_column=sa.Column(sa.Boolean, nullable=False, server_default=false())) + + def ensure_is_message(self) -> None: + if not self.payload or not isinstance(self.payload.payload, MessagePayload): + raise OasstError("Invalid message", OasstErrorCode.INVALID_MESSAGE, HTTPStatus.INTERNAL_SERVER_ERROR) + + @property + def text(self) -> str: + self.ensure_is_message() + return self.payload.payload.text diff --git a/backend/oasst_backend/models/task.py b/backend/oasst_backend/models/task.py index 356eafea..a980c1b5 100644 --- a/backend/oasst_backend/models/task.py +++ b/backend/oasst_backend/models/task.py @@ -22,7 +22,7 @@ class Task(SQLModel, table=True): sa_column=sa.Column(sa.DateTime(), nullable=False, server_default=sa.func.current_timestamp()), ) expiry_date: Optional[datetime] = Field(sa_column=sa.Column(sa.DateTime(), nullable=True)) - user_id: UUID = Field(nullable=True, foreign_key="user.id", index=True) + user_id: Optional[UUID] = Field(nullable=True, foreign_key="user.id", index=True) payload_type: str = Field(nullable=False, max_length=200) payload: PayloadContainer = Field(sa_column=sa.Column(payload_column_type(PayloadContainer), nullable=False)) api_client_id: UUID = Field(nullable=False, foreign_key="api_client.id") diff --git a/backend/oasst_backend/schemas/text_labels.py b/backend/oasst_backend/schemas/text_labels.py new file mode 100644 index 00000000..9135c558 --- /dev/null +++ b/backend/oasst_backend/schemas/text_labels.py @@ -0,0 +1,13 @@ +from typing import Optional + +from pydantic import BaseModel + + +class LabelOption(BaseModel): + name: str + display_text: str + help_text: Optional[str] + + +class ValidLabelsResponse(BaseModel): + valid_labels: list[LabelOption] diff --git a/backend/test_data/generic/test_generic_data.json b/backend/test_data/generic/test_generic_data.json new file mode 100644 index 00000000..4b4b4a39 --- /dev/null +++ b/backend/test_data/generic/test_generic_data.json @@ -0,0 +1,72 @@ +[ + { + "task_message_id": "de111fa8", + "user_message_id": "6f1d0711", + "parent_message_id": null, + "text": "Hi!", + "role": "prompter" + }, + { + "task_message_id": "74c381d4", + "user_message_id": "4a24530b", + "parent_message_id": "6f1d0711", + "text": "Hello! How can I help you?", + "role": "assistant" + }, + { + "task_message_id": "3d5dc440", + "user_message_id": "a8c01c04", + "parent_message_id": "4a24530b", + "text": "Do you have a recipe for potato soup?", + "role": "prompter" + }, + { + "task_message_id": "643716c1", + "user_message_id": "f43a93b7", + "parent_message_id": "4a24530b", + "text": "Who were the 8 presidents before George Washington?", + "role": "prompter" + }, + { + "task_message_id": "2e4e1e6", + "user_message_id": "c886920", + "parent_message_id": "6f1d0711", + "text": "Hey buddy! How can I serve you?", + "role": "assistant" + }, + { + "task_message_id": "970c437d", + "user_message_id": "cec432cf", + "parent_message_id": null, + "text": "euirdteunvglfe23908230892309832098 AAAAAAAA", + "role": "prompter" + }, + { + "task_message_id": "6066118e", + "user_message_id": "4f85f637", + "parent_message_id": "cec432cf", + "text": "Sorry, I did not understand your request and it is unclear to me what you want me to do. Could you describe it in a different way?", + "role": "assistant" + }, + { + "task_message_id": "ba87780d", + "user_message_id": "0e276b98", + "parent_message_id": "cec432cf", + "text": "I'm unsure how to interpret this. Is it a riddle?", + "role": "assistant" + }, + { + "task_message_id": "b8e98ed6", + "user_message_id": "89384709", + "parent_message_id": "0e276b98", + "text": "No, I just wanted to see how you reply when I type random characters. Can you tell me who invented Wikipedia?", + "role": "prompter" + }, + { + "task_message_id": "9a0e7683", + "user_message_id": "6d452c57", + "parent_message_id": "0e276b98", + "text": "Sorry, my cat sat on my keyboard. Can you print a cat in ASCII art?", + "role": "prompter" + } +] diff --git a/docker/Dockerfile.backend b/docker/Dockerfile.backend index 1f3bdfcd..c89a0280 100644 --- a/docker/Dockerfile.backend +++ b/docker/Dockerfile.backend @@ -14,3 +14,4 @@ COPY ./backend/alembic /app/alembic COPY ./backend/alembic.ini /app/alembic.ini COPY ./backend/main.py /app/main.py COPY ./backend/oasst_backend /app/oasst_backend +COPY ./backend/test_data /app/test_data diff --git a/docs/README.md b/docs/README.md index 0d6fa482..7189d5da 100644 --- a/docs/README.md +++ b/docs/README.md @@ -1,7 +1,9 @@ -# Website +# Docs Site -This website is built using [Docusaurus 2](https://docusaurus.io/), a modern -static website generator. +https://laion-ai.github.io/Open-Assistant/ + +This [site](https://laion-ai.github.io/Open-Assistant/) is built using +[Docusaurus 2](https://docusaurus.io/), a modern static website generator. ### Contributing diff --git a/docs/docusaurus.config.js b/docs/docusaurus.config.js index 2d902d83..4e456369 100644 --- a/docs/docusaurus.config.js +++ b/docs/docusaurus.config.js @@ -20,7 +20,7 @@ const config = { // If you aren't using GitHub pages, you don't need these. organizationName: "LAION-AI", // Usually your GitHub org/user name. projectName: "Open-Assistant", // Usually your repo name. - deploymentBranch: "docs-site-poc", + deploymentBranch: "main", // Even if you don't use internalization, you can use this field to set useful // metadata like html lang. For example, if your site is Chinese, you may want diff --git a/model/reward/instructor/configs/deberta-v2-xlarge.yml b/model/reward/instructor/configs/deberta-v2-xlarge.yml new file mode 100644 index 00000000..8bc4a182 --- /dev/null +++ b/model/reward/instructor/configs/deberta-v2-xlarge.yml @@ -0,0 +1,15 @@ +model_name: microsoft/deberta-v2-xlarge +learning_rate: 1e-5 +freeze_layer: 15 +scheduler: cosine +gradient_checkpointing: false +gradient_accumulation_steps: 16 +per_device_train_batch_size: 1 +warmup_steps: 600 +eval_steps: 200 +save_steps: 500 +max_length: 512 +num_train_epochs: 2 +datasets: + - webgpt + - hfsummary diff --git a/model/reward/instructor/configs/deberta-v3-base.yml b/model/reward/instructor/configs/deberta-v3-base.yml new file mode 100644 index 00000000..7023709c --- /dev/null +++ b/model/reward/instructor/configs/deberta-v3-base.yml @@ -0,0 +1,14 @@ +model_name: microsoft/deberta-v3-base +learning_rate: 1e-5 +scheduler: cosine +gradient_checkpointing: false +gradient_accumulation_steps: 32 +per_device_train_batch_size: 2 +warmup_steps: 600 +eval_steps: 200 +save_steps: 500 +max_length: 512 +num_train_epochs: 2 +datasets: + - webgpt + - hfsummary diff --git a/model/reward/instructor/configs/deberta-v3-large-squad2.yml b/model/reward/instructor/configs/deberta-v3-large-squad2.yml new file mode 100644 index 00000000..47275309 --- /dev/null +++ b/model/reward/instructor/configs/deberta-v3-large-squad2.yml @@ -0,0 +1,13 @@ +model_name: deepset/deberta-v3-large-squad2 +learning_rate: 1e-5 +gradient_checkpointing: false +gradient_accumulation_steps: 32 +per_device_train_batch_size: 1 +warmup_steps: 600 +eval_steps: 200 +save_steps: 500 +max_length: 512 +num_train_epochs: 2 +datasets: + - webgpt + - hfsummary diff --git a/model/reward/instructor/configs/deberta-v3-large.yml b/model/reward/instructor/configs/deberta-v3-large.yml new file mode 100644 index 00000000..0a910408 --- /dev/null +++ b/model/reward/instructor/configs/deberta-v3-large.yml @@ -0,0 +1,14 @@ +model_name: microsoft/deberta-v3-large +learning_rate: 1e-5 +scheduler: cosine +gradient_checkpointing: false +gradient_accumulation_steps: 32 +per_device_train_batch_size: 1 +warmup_steps: 600 +eval_steps: 200 +save_steps: 500 +max_length: 512 +num_train_epochs: 2 +datasets: + - webgpt + - hfsummary diff --git a/model/reward/instructor/trainer.py b/model/reward/instructor/trainer.py index f9266d70..68a58a38 100644 --- a/model/reward/instructor/trainer.py +++ b/model/reward/instructor/trainer.py @@ -11,6 +11,7 @@ from rank_datasets import DataCollatorForPairRank, HFSummary, RankGenCollator, W from torch import nn from torch.utils.data import ConcatDataset, Dataset from transformers import ( + AdamW, AutoModelForSequenceClassification, DataCollator, EvalPrediction, @@ -19,6 +20,8 @@ from transformers import ( Trainer, TrainerCallback, TrainingArguments, + get_cosine_schedule_with_warmup, + get_linear_schedule_with_warmup, ) from utils import argument_parsing, freeze_top_n_layers, get_tokenizer, train_val_dataset @@ -179,7 +182,7 @@ if __name__ == "__main__": evaluation_strategy="steps", eval_steps=training_conf["eval_steps"], save_steps=1000, - report_to="local", + report_to="wandb", ) train_datasets, evals = [], {} if "webgpt" in training_conf["datasets"]: @@ -202,6 +205,21 @@ if __name__ == "__main__": else: collate_fn = DataCollatorForPairRank(tokenizer, max_length=training_conf["max_length"]) assert len(evals) > 0 + + optimizer = AdamW(model.parameters(), lr=args.learning_rate, weight_decay=args.weight_decay) + scheduler = None + if "scheduler" in training_conf: + if training_conf["scheduler"] == "linear": + scheduler = get_linear_schedule_with_warmup() + elif training_conf["scheduler"] == "cosine": + scheduler = get_cosine_schedule_with_warmup( + optimizer, + num_warmup_steps=args.warmup_steps, + num_training_steps=len(train) + * args.num_train_epochs + / (args.per_device_train_batch_size * args.gradient_accumulation_steps), + ) + trainer = RankTrainer( model=model, model_name=model_name, @@ -211,6 +229,7 @@ if __name__ == "__main__": data_collator=collate_fn, tokenizer=tokenizer, compute_metrics=compute_metrics, + optimizers=(optimizer, scheduler), ) # trainer.evaluate() trainer.train() diff --git a/notebooks/code-bugger/openbugger_example.ipynb b/notebooks/code-bugger/openbugger_example.ipynb index 22e9b0c8..6e2acd27 100644 --- a/notebooks/code-bugger/openbugger_example.ipynb +++ b/notebooks/code-bugger/openbugger_example.ipynb @@ -1,5 +1,13 @@ { "cells": [ + { + "attachments": {}, + "cell_type": "markdown", + "metadata": {}, + "source": [ + "[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/LAION-AI/Open-Assistant/blob/main/notebooks/code-bugger/openbugger_example.ipynb)" + ] + }, { "cell_type": "code", "execution_count": null, diff --git a/notebooks/data-argumentation/EssayInstructions.ipynb b/notebooks/data-argumentation/EssayInstructions.ipynb index c4179382..30834d32 100644 --- a/notebooks/data-argumentation/EssayInstructions.ipynb +++ b/notebooks/data-argumentation/EssayInstructions.ipynb @@ -1,5 +1,13 @@ { "cells": [ + { + "attachments": {}, + "cell_type": "markdown", + "metadata": {}, + "source": [ + "[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/LAION-AI/Open-Assistant/blob/main/notebooks/data-argumentation/EssayInstructions.ipynb)" + ] + }, { "cell_type": "code", "execution_count": null, diff --git a/notebooks/data-argumentation/EssayRevision.ipynb b/notebooks/data-argumentation/EssayRevision.ipynb index cba9bc5b..2397131c 100644 --- a/notebooks/data-argumentation/EssayRevision.ipynb +++ b/notebooks/data-argumentation/EssayRevision.ipynb @@ -1,5 +1,13 @@ { "cells": [ + { + "attachments": {}, + "cell_type": "markdown", + "metadata": {}, + "source": [ + "[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/LAION-AI/Open-Assistant/blob/main/notebooks/data-argumentation/EssayRevision.ipynb)" + ] + }, { "cell_type": "markdown", "metadata": { diff --git a/notebooks/data-argumentation/StackExchangeBuilder.ipynb b/notebooks/data-argumentation/StackExchangeBuilder.ipynb index 625d757b..b0dd9a8b 100644 --- a/notebooks/data-argumentation/StackExchangeBuilder.ipynb +++ b/notebooks/data-argumentation/StackExchangeBuilder.ipynb @@ -1,28 +1,22 @@ { - "nbformat": 4, - "nbformat_minor": 0, - "metadata": { - "colab": { - "provenance": [] - }, - "kernelspec": { - "name": "python3", - "display_name": "Python 3" - }, - "language_info": { - "name": "python" - } - }, "cells": [ { + "attachments": {}, "cell_type": "markdown", + "metadata": {}, + "source": [ + "[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/LAION-AI/Open-Assistant/blob/main/notebooks/data-argumentation/StackExchangeBuilder.ipynb)" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "TB7CEfs8F-8u" + }, "source": [ "# Ingest StackExchange data dumps\n", "This notebook takes a StackExchange Data dump \"Posts.xml\" file and ingests it into a Pandas Dataframe. Outputs of the file can be JSON, JSONL, Parquet, or CSV. " - ], - "metadata": { - "id": "TB7CEfs8F-8u" - } + ] }, { "cell_type": "code", @@ -40,16 +34,34 @@ }, { "cell_type": "markdown", + "metadata": { + "id": "15mAL7GnzBv0" + }, "source": [ "# Extract StackExchange\n", "Pull StackExchange file dumps. Specific column types are enforced to prevent errors on processing later in the notebook" - ], - "metadata": { - "id": "15mAL7GnzBv0" - } + ] }, { "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "FtcvUEaHVxcW", + "outputId": "5b0cb19d-e3d9-422b-9077-52241bd09e0e" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "dict_keys(['3dprinting_meta', '3dprinting', 'Stackoverflow_com_Posts_7z', 'academia_meta', 'academia', 'ai_meta', 'ai', 'android_meta', 'android', 'anime_meta', 'anime', 'apple_meta', 'apple', 'arduino_meta', 'arduino', 'askubuntu_com_7z', 'astronomy_meta', 'astronomy', 'aviation_meta', 'aviation', 'avp_meta', 'avp', 'beer_meta', 'beer', 'bicycles_meta', 'bicycles', 'bioacoustics_meta', 'bioacoustics', 'bioinformatics_meta', 'bioinformatics', 'biology_meta', 'biology', 'bitcoin_meta', 'bitcoin', 'blender_meta', 'blender', 'boardgames_meta', 'boardgames', 'bricks_meta', 'bricks', 'buddhism_meta', 'buddhism', 'cardano_meta', 'cardano', 'chemistry_meta', 'chemistry', 'chess_meta', 'chess', 'chinese_meta', 'chinese', 'christianity_meta', 'christianity', 'civicrm_meta', 'civicrm', 'codegolf_meta', 'codegolf', 'codereview_meta', 'codereview', 'coffee_meta', 'coffee', 'cogsci_meta', 'cogsci', 'computergraphics_meta', 'computergraphics', 'conlang_meta', 'conlang', 'cooking_meta', 'cooking', 'craftcms_meta', 'craftcms', 'crafts_meta', 'crafts', 'crypto_meta', 'crypto', 'cs_meta', 'cs', 'cseducators_meta', 'cseducators', 'cstheory_meta', 'cstheory', 'datascience_meta', 'datascience', 'dba_meta', 'dba', 'devops_meta', 'devops', 'diy_meta', 'diy', 'drones_meta', 'drones', 'drupal_meta', 'drupal', 'dsp_meta', 'dsp', 'earthscience_meta', 'earthscience', 'ebooks_meta', 'ebooks', 'economics_meta', 'economics', 'electronics_meta', 'electronics', 'elementaryos_meta', 'elementaryos', 'ell_meta', 'ell', 'emacs_meta', 'emacs', 'engineering_meta', 'engineering', 'english_meta', 'english', 'eosio_meta', 'eosio', 'es_meta_stackoverflow_com_7z', 'es_stackoverflow_com_7z', 'esperanto_meta', 'esperanto', 'ethereum_meta', 'ethereum', 'expatriates_meta', 'expatriates', 'expressionengine_meta', 'expressionengine', 'fitness_meta', 'fitness', 'freelancing_meta', 'freelancing', 'french_meta', 'french', 'gamedev_meta', 'gamedev', 'gaming_meta', 'gaming', 'gardening_meta', 'gardening', 'genealogy_meta', 'genealogy', 'german_meta', 'german', 'gis_meta', 'gis', 'graphicdesign_meta', 'graphicdesign', 'ham_meta', 'ham', 'hardwarerecs_meta', 'hardwarerecs', 'health_meta', 'health', 'hermeneutics_meta', 'hermeneutics', 'hinduism_meta', 'hinduism', 'history_meta', 'history', 'homebrew_meta', 'homebrew', 'hsm_meta', 'hsm', 'interpersonal_meta', 'interpersonal', 'iot_meta', 'iot', 'iota_meta', 'iota', 'islam_meta', 'islam', 'italian_meta', 'italian', 'ja_meta_stackoverflow_com_7z', 'ja_stackoverflow_com_7z', 'japanese_meta', 'japanese', 'joomla_meta', 'joomla', 'judaism_meta', 'judaism', 'korean_meta', 'korean', 'languagelearning_meta', 'languagelearning', 'latin_meta', 'latin', 'law_meta', 'law', 'lifehacks_meta', 'lifehacks', 'linguistics_meta', 'linguistics', 'literature_meta', 'literature', 'magento_meta', 'magento', 'martialarts_meta', 'martialarts', 'materials_meta', 'materials', 'math_meta', 'math', 'matheducators_meta', 'matheducators', 'mathematica_meta', 'mathematica', 'mathoverflow_net_7z', 'mechanics_meta', 'mechanics', 'meta_askubuntu_com_7z', 'meta_mathoverflow_net_7z', 'meta_serverfault_com_7z', 'meta', 'meta_stackoverflow_com_7z', 'meta_superuser_com_7z', 'moderators_meta', 'moderators', 'monero_meta', 'monero', 'money_meta', 'money', 'movies_meta', 'movies', 'music_meta', 'music', 'musicfans_meta', 'musicfans', 'mythology_meta', 'mythology', 'networkengineering_meta', 'networkengineering', 'opendata_meta', 'opendata', 'opensource_meta', 'opensource', 'or_meta', 'or', 'outdoors_meta', 'outdoors', 'parenting_meta', 'parenting', 'patents_meta', 'patents', 'pets_meta', 'pets', 'philosophy_meta', 'philosophy', 'photo_meta', 'photo', 'physics_meta', 'physics', 'pm_meta', 'pm', 'poker_meta', 'poker', 'politics_meta', 'politics', 'portuguese_meta', 'portuguese', 'proofassistants_meta', 'proofassistants', 'pt_meta_stackoverflow_com_7z', 'pt_stackoverflow_com_7z', 'puzzling_meta', 'puzzling', 'quant_meta', 'quant', 'quantumcomputing_meta', 'quantumcomputing', 'raspberrypi_meta', 'raspberrypi', 'retrocomputing_meta', 'retrocomputing', 'reverseengineering_meta', 'reverseengineering', 'robotics_meta', 'robotics', 'rpg_meta', 'rpg', 'ru_meta_stackoverflow_com_7z', 'ru_stackoverflow_com_7z', 'rus_meta', 'rus', 'russian_meta', 'russian', 'salesforce_meta', 'salesforce', 'scicomp_meta', 'scicomp', 'scifi_meta', 'scifi', 'security_meta', 'security', 'serverfault_com_7z', 'sharepoint_meta', 'sharepoint', 'sitecore_meta', 'sitecore', 'skeptics_meta', 'skeptics', 'softwareengineering_meta', 'softwareengineering', 'softwarerecs_meta', 'softwarerecs', 'solana_meta', 'solana', 'sound_meta', 'sound', 'space_meta', 'space', 'spanish_meta', 'spanish', 'sports_meta', 'sports', 'sqa_meta', 'sqa', 'stackapps_com_7z', 'stackoverflow_com_Badges_7z', 'stackoverflow_com_Comments_7z', 'stackoverflow_com_PostHistory_7z', 'stackoverflow_com_PostLinks_7z', 'stackoverflow_com_Tags_7z', 'stackoverflow_com_Users_7z', 'stackoverflow_com_Votes_7z', 'stats_meta', 'stats', 'stellar_meta', 'stellar', 'substrate_meta', 'substrate', 'superuser_com_7z', 'sustainability_meta', 'sustainability', 'tex_meta', 'tex', 'tezos_meta', 'tezos', 'tor_meta', 'tor', 'travel_meta', 'travel', 'tridion_meta', 'tridion', 'ukrainian_meta', 'ukrainian', 'unix_meta', 'unix', 'ux_meta', 'ux', 'vegetarianism_meta', 'vegetarianism', 'vi_meta', 'vi', 'webapps_meta', 'webapps', 'webmasters_meta', 'webmasters', 'windowsphone_meta', 'windowsphone', 'woodworking_meta', 'woodworking', 'wordpress_meta', 'wordpress', 'workplace_meta', 'workplace', 'worldbuilding_meta', 'worldbuilding', 'writers_meta', 'writers'])\n", + "https://ia600107.us.archive.org/view_archive.php?archive=/27/items/stackexchange/ai.stackexchange.com.7z&file=Posts.xml\n" + ] + } + ], "source": [ "base_url = \"https://ia600107.us.archive.org/view_archive.php?archive=/27/items/stackexchange/{0}&file=Posts.xml\"\n", "\n", @@ -73,90 +85,11 @@ "\n", "print(urls.keys())\n", "print(urls.get(\"ai\"))" - ], - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "FtcvUEaHVxcW", - "outputId": "5b0cb19d-e3d9-422b-9077-52241bd09e0e" - }, - "execution_count": null, - "outputs": [ - { - "output_type": "stream", - "name": "stdout", - "text": [ - "dict_keys(['3dprinting_meta', '3dprinting', 'Stackoverflow_com_Posts_7z', 'academia_meta', 'academia', 'ai_meta', 'ai', 'android_meta', 'android', 'anime_meta', 'anime', 'apple_meta', 'apple', 'arduino_meta', 'arduino', 'askubuntu_com_7z', 'astronomy_meta', 'astronomy', 'aviation_meta', 'aviation', 'avp_meta', 'avp', 'beer_meta', 'beer', 'bicycles_meta', 'bicycles', 'bioacoustics_meta', 'bioacoustics', 'bioinformatics_meta', 'bioinformatics', 'biology_meta', 'biology', 'bitcoin_meta', 'bitcoin', 'blender_meta', 'blender', 'boardgames_meta', 'boardgames', 'bricks_meta', 'bricks', 'buddhism_meta', 'buddhism', 'cardano_meta', 'cardano', 'chemistry_meta', 'chemistry', 'chess_meta', 'chess', 'chinese_meta', 'chinese', 'christianity_meta', 'christianity', 'civicrm_meta', 'civicrm', 'codegolf_meta', 'codegolf', 'codereview_meta', 'codereview', 'coffee_meta', 'coffee', 'cogsci_meta', 'cogsci', 'computergraphics_meta', 'computergraphics', 'conlang_meta', 'conlang', 'cooking_meta', 'cooking', 'craftcms_meta', 'craftcms', 'crafts_meta', 'crafts', 'crypto_meta', 'crypto', 'cs_meta', 'cs', 'cseducators_meta', 'cseducators', 'cstheory_meta', 'cstheory', 'datascience_meta', 'datascience', 'dba_meta', 'dba', 'devops_meta', 'devops', 'diy_meta', 'diy', 'drones_meta', 'drones', 'drupal_meta', 'drupal', 'dsp_meta', 'dsp', 'earthscience_meta', 'earthscience', 'ebooks_meta', 'ebooks', 'economics_meta', 'economics', 'electronics_meta', 'electronics', 'elementaryos_meta', 'elementaryos', 'ell_meta', 'ell', 'emacs_meta', 'emacs', 'engineering_meta', 'engineering', 'english_meta', 'english', 'eosio_meta', 'eosio', 'es_meta_stackoverflow_com_7z', 'es_stackoverflow_com_7z', 'esperanto_meta', 'esperanto', 'ethereum_meta', 'ethereum', 'expatriates_meta', 'expatriates', 'expressionengine_meta', 'expressionengine', 'fitness_meta', 'fitness', 'freelancing_meta', 'freelancing', 'french_meta', 'french', 'gamedev_meta', 'gamedev', 'gaming_meta', 'gaming', 'gardening_meta', 'gardening', 'genealogy_meta', 'genealogy', 'german_meta', 'german', 'gis_meta', 'gis', 'graphicdesign_meta', 'graphicdesign', 'ham_meta', 'ham', 'hardwarerecs_meta', 'hardwarerecs', 'health_meta', 'health', 'hermeneutics_meta', 'hermeneutics', 'hinduism_meta', 'hinduism', 'history_meta', 'history', 'homebrew_meta', 'homebrew', 'hsm_meta', 'hsm', 'interpersonal_meta', 'interpersonal', 'iot_meta', 'iot', 'iota_meta', 'iota', 'islam_meta', 'islam', 'italian_meta', 'italian', 'ja_meta_stackoverflow_com_7z', 'ja_stackoverflow_com_7z', 'japanese_meta', 'japanese', 'joomla_meta', 'joomla', 'judaism_meta', 'judaism', 'korean_meta', 'korean', 'languagelearning_meta', 'languagelearning', 'latin_meta', 'latin', 'law_meta', 'law', 'lifehacks_meta', 'lifehacks', 'linguistics_meta', 'linguistics', 'literature_meta', 'literature', 'magento_meta', 'magento', 'martialarts_meta', 'martialarts', 'materials_meta', 'materials', 'math_meta', 'math', 'matheducators_meta', 'matheducators', 'mathematica_meta', 'mathematica', 'mathoverflow_net_7z', 'mechanics_meta', 'mechanics', 'meta_askubuntu_com_7z', 'meta_mathoverflow_net_7z', 'meta_serverfault_com_7z', 'meta', 'meta_stackoverflow_com_7z', 'meta_superuser_com_7z', 'moderators_meta', 'moderators', 'monero_meta', 'monero', 'money_meta', 'money', 'movies_meta', 'movies', 'music_meta', 'music', 'musicfans_meta', 'musicfans', 'mythology_meta', 'mythology', 'networkengineering_meta', 'networkengineering', 'opendata_meta', 'opendata', 'opensource_meta', 'opensource', 'or_meta', 'or', 'outdoors_meta', 'outdoors', 'parenting_meta', 'parenting', 'patents_meta', 'patents', 'pets_meta', 'pets', 'philosophy_meta', 'philosophy', 'photo_meta', 'photo', 'physics_meta', 'physics', 'pm_meta', 'pm', 'poker_meta', 'poker', 'politics_meta', 'politics', 'portuguese_meta', 'portuguese', 'proofassistants_meta', 'proofassistants', 'pt_meta_stackoverflow_com_7z', 'pt_stackoverflow_com_7z', 'puzzling_meta', 'puzzling', 'quant_meta', 'quant', 'quantumcomputing_meta', 'quantumcomputing', 'raspberrypi_meta', 'raspberrypi', 'retrocomputing_meta', 'retrocomputing', 'reverseengineering_meta', 'reverseengineering', 'robotics_meta', 'robotics', 'rpg_meta', 'rpg', 'ru_meta_stackoverflow_com_7z', 'ru_stackoverflow_com_7z', 'rus_meta', 'rus', 'russian_meta', 'russian', 'salesforce_meta', 'salesforce', 'scicomp_meta', 'scicomp', 'scifi_meta', 'scifi', 'security_meta', 'security', 'serverfault_com_7z', 'sharepoint_meta', 'sharepoint', 'sitecore_meta', 'sitecore', 'skeptics_meta', 'skeptics', 'softwareengineering_meta', 'softwareengineering', 'softwarerecs_meta', 'softwarerecs', 'solana_meta', 'solana', 'sound_meta', 'sound', 'space_meta', 'space', 'spanish_meta', 'spanish', 'sports_meta', 'sports', 'sqa_meta', 'sqa', 'stackapps_com_7z', 'stackoverflow_com_Badges_7z', 'stackoverflow_com_Comments_7z', 'stackoverflow_com_PostHistory_7z', 'stackoverflow_com_PostLinks_7z', 'stackoverflow_com_Tags_7z', 'stackoverflow_com_Users_7z', 'stackoverflow_com_Votes_7z', 'stats_meta', 'stats', 'stellar_meta', 'stellar', 'substrate_meta', 'substrate', 'superuser_com_7z', 'sustainability_meta', 'sustainability', 'tex_meta', 'tex', 'tezos_meta', 'tezos', 'tor_meta', 'tor', 'travel_meta', 'travel', 'tridion_meta', 'tridion', 'ukrainian_meta', 'ukrainian', 'unix_meta', 'unix', 'ux_meta', 'ux', 'vegetarianism_meta', 'vegetarianism', 'vi_meta', 'vi', 'webapps_meta', 'webapps', 'webmasters_meta', 'webmasters', 'windowsphone_meta', 'windowsphone', 'woodworking_meta', 'woodworking', 'wordpress_meta', 'wordpress', 'workplace_meta', 'workplace', 'worldbuilding_meta', 'worldbuilding', 'writers_meta', 'writers'])\n", - "https://ia600107.us.archive.org/view_archive.php?archive=/27/items/stackexchange/ai.stackexchange.com.7z&file=Posts.xml\n" - ] - } ] }, { "cell_type": "code", - "source": [ - "xml_format_map = {\n", - " \"Id\": int,\n", - " \"PostTypeId\": int,\n", - " \"CreationDate\": str,\n", - " \"Score\": int,\n", - " \"ViewCount\": int,\n", - " \"Body\": str,\n", - " \"AnswerCount\": int,\n", - " \"CommentCount\": int,\n", - " \"ContentLicense\": str,\n", - " \"AcceptedAnswerId\": int,\n", - " \"ParentId\": int,\n", - "}\n", - "\n", - "\n", - "# def extract_xml_file(file_url: str):\n", - "# table = pd.read_xml(file_url)\n", - "# return table\n", - "\n", - "\n", - "def xml_to_df(response: str):\n", - " \"\"\"\n", - " Collect and Manually import XML into Dataframe\n", - "\n", - " pd.read_xml() errors when XML trees are too large, this is just a hack to\n", - " download a XML file and parse into a Dataframe. **Not Tested on huge XML files**\n", - "\n", - " Parameters:\n", - " response (Requests.Response): Requests response object with the XML data\n", - "\n", - " Returns:\n", - " df (DataFrame): A Dataframe from the XML file\n", - " \"\"\"\n", - " soup = bs(response.content, \"xml\")\n", - " posts = soup.find_all(\"row\")\n", - "\n", - " all_posts = [post.attrs for post in posts]\n", - "\n", - " df = pd.DataFrame(all_posts)\n", - " df.AnswerCount.fillna(0, inplace=True)\n", - " df.ViewCount.fillna(0, inplace=True)\n", - " df.AcceptedAnswerId.fillna(0, inplace=True)\n", - " df.ParentId.fillna(0, inplace=True)\n", - " df[\"DataSource\"] = response.url\n", - " df = df.astype(xml_format_map)\n", - " return df\n", - "\n", - "\n", - "dataset_name = \"ai\"\n", - "\n", - "xml_posts_path = urls.get(dataset_name)\n", - "\n", - "\n", - "# df = extract_xml_file(test)\n", - "response = requests.get(xml_posts_path)\n", - "df = xml_to_df(response)\n", - "\n", - "\n", - "print(df.dtypes)\n", - "df.head()" - ], + "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/", @@ -165,11 +98,10 @@ "id": "-t27RnxdzBYB", "outputId": "5ec0ceed-c82b-48fa-facd-41b4aae2f9e6" }, - "execution_count": null, "outputs": [ { - "output_type": "stream", "name": "stdout", + "output_type": "stream", "text": [ "Id int64\n", "PostTypeId int64\n", @@ -198,53 +130,7 @@ ] }, { - "output_type": "execute_result", "data": { - "text/plain": [ - " Id PostTypeId AcceptedAnswerId CreationDate Score \\\n", - "0 1 1 3 2016-08-02T15:39:14.947 10 \n", - "1 2 1 9 2016-08-02T15:40:20.623 14 \n", - "2 3 2 0 2016-08-02T15:40:24.820 15 \n", - "3 4 1 12 2016-08-02T15:41:22.020 33 \n", - "4 6 1 20 2016-08-02T15:43:35.460 7 \n", - "\n", - " ViewCount Body OwnerUserId \\\n", - "0 710

What does \"backprop\" mean? Is the \"backprop... 8 \n", - "1 1008

Does increasing the noise in data help to i... 8 \n", - "2 0

\"Backprop\" is the same as \"backpropagation\"... 4 \n", - "3 1266

When you're writing your algorithm, how do ... 8 \n", - "4 279

Given the following definition of an intell... 29 \n", - "\n", - " LastEditorUserId LastEditDate ... AnswerCount CommentCount \\\n", - "0 2444 2019-11-16T17:56:22.093 ... 5 0 \n", - "1 2444 2019-02-23T22:36:19.090 ... 3 0 \n", - "2 NaN NaN ... 0 0 \n", - "3 2444 2021-01-19T23:54:07.813 ... 4 0 \n", - "4 2444 2019-06-15T18:25:58.513 ... 2 0 \n", - "\n", - " ContentLicense ParentId ClosedDate FavoriteCount CommunityOwnedDate \\\n", - "0 CC BY-SA 4.0 0 NaN NaN NaN \n", - "1 CC BY-SA 4.0 0 NaN NaN NaN \n", - "2 CC BY-SA 3.0 1 NaN NaN NaN \n", - "3 CC BY-SA 3.0 0 NaN NaN NaN \n", - "4 CC BY-SA 4.0 0 NaN NaN NaN \n", - "\n", - " LastEditorDisplayName OwnerDisplayName \\\n", - "0 NaN NaN \n", - "1 NaN NaN \n", - "2 NaN NaN \n", - "3 NaN NaN \n", - "4 NaN NaN \n", - "\n", - " DataSource \n", - "0 https://ia600107.us.archive.org/view_archive.p... \n", - "1 https://ia600107.us.archive.org/view_archive.p... \n", - "2 https://ia600107.us.archive.org/view_archive.p... \n", - "3 https://ia600107.us.archive.org/view_archive.p... \n", - "4 https://ia600107.us.archive.org/view_archive.p... \n", - "\n", - "[5 rows x 23 columns]" - ], "text/html": [ "\n", "

\n", @@ -491,99 +377,133 @@ "
\n", "
\n", " " + ], + "text/plain": [ + " Id PostTypeId AcceptedAnswerId CreationDate Score \\\n", + "0 1 1 3 2016-08-02T15:39:14.947 10 \n", + "1 2 1 9 2016-08-02T15:40:20.623 14 \n", + "2 3 2 0 2016-08-02T15:40:24.820 15 \n", + "3 4 1 12 2016-08-02T15:41:22.020 33 \n", + "4 6 1 20 2016-08-02T15:43:35.460 7 \n", + "\n", + " ViewCount Body OwnerUserId \\\n", + "0 710

What does \"backprop\" mean? Is the \"backprop... 8 \n", + "1 1008

Does increasing the noise in data help to i... 8 \n", + "2 0

\"Backprop\" is the same as \"backpropagation\"... 4 \n", + "3 1266

When you're writing your algorithm, how do ... 8 \n", + "4 279

Given the following definition of an intell... 29 \n", + "\n", + " LastEditorUserId LastEditDate ... AnswerCount CommentCount \\\n", + "0 2444 2019-11-16T17:56:22.093 ... 5 0 \n", + "1 2444 2019-02-23T22:36:19.090 ... 3 0 \n", + "2 NaN NaN ... 0 0 \n", + "3 2444 2021-01-19T23:54:07.813 ... 4 0 \n", + "4 2444 2019-06-15T18:25:58.513 ... 2 0 \n", + "\n", + " ContentLicense ParentId ClosedDate FavoriteCount CommunityOwnedDate \\\n", + "0 CC BY-SA 4.0 0 NaN NaN NaN \n", + "1 CC BY-SA 4.0 0 NaN NaN NaN \n", + "2 CC BY-SA 3.0 1 NaN NaN NaN \n", + "3 CC BY-SA 3.0 0 NaN NaN NaN \n", + "4 CC BY-SA 4.0 0 NaN NaN NaN \n", + "\n", + " LastEditorDisplayName OwnerDisplayName \\\n", + "0 NaN NaN \n", + "1 NaN NaN \n", + "2 NaN NaN \n", + "3 NaN NaN \n", + "4 NaN NaN \n", + "\n", + " DataSource \n", + "0 https://ia600107.us.archive.org/view_archive.p... \n", + "1 https://ia600107.us.archive.org/view_archive.p... \n", + "2 https://ia600107.us.archive.org/view_archive.p... \n", + "3 https://ia600107.us.archive.org/view_archive.p... \n", + "4 https://ia600107.us.archive.org/view_archive.p... \n", + "\n", + "[5 rows x 23 columns]" ] }, + "execution_count": 219, "metadata": {}, - "execution_count": 219 + "output_type": "execute_result" } + ], + "source": [ + "xml_format_map = {\n", + " \"Id\": int,\n", + " \"PostTypeId\": int,\n", + " \"CreationDate\": str,\n", + " \"Score\": int,\n", + " \"ViewCount\": int,\n", + " \"Body\": str,\n", + " \"AnswerCount\": int,\n", + " \"CommentCount\": int,\n", + " \"ContentLicense\": str,\n", + " \"AcceptedAnswerId\": int,\n", + " \"ParentId\": int,\n", + "}\n", + "\n", + "\n", + "# def extract_xml_file(file_url: str):\n", + "# table = pd.read_xml(file_url)\n", + "# return table\n", + "\n", + "\n", + "def xml_to_df(response: str):\n", + " \"\"\"\n", + " Collect and Manually import XML into Dataframe\n", + "\n", + " pd.read_xml() errors when XML trees are too large, this is just a hack to\n", + " download a XML file and parse into a Dataframe. **Not Tested on huge XML files**\n", + "\n", + " Parameters:\n", + " response (Requests.Response): Requests response object with the XML data\n", + "\n", + " Returns:\n", + " df (DataFrame): A Dataframe from the XML file\n", + " \"\"\"\n", + " soup = bs(response.content, \"xml\")\n", + " posts = soup.find_all(\"row\")\n", + "\n", + " all_posts = [post.attrs for post in posts]\n", + "\n", + " df = pd.DataFrame(all_posts)\n", + " df.AnswerCount.fillna(0, inplace=True)\n", + " df.ViewCount.fillna(0, inplace=True)\n", + " df.AcceptedAnswerId.fillna(0, inplace=True)\n", + " df.ParentId.fillna(0, inplace=True)\n", + " df[\"DataSource\"] = response.url\n", + " df = df.astype(xml_format_map)\n", + " return df\n", + "\n", + "\n", + "dataset_name = \"ai\"\n", + "\n", + "xml_posts_path = urls.get(dataset_name)\n", + "\n", + "\n", + "# df = extract_xml_file(test)\n", + "response = requests.get(xml_posts_path)\n", + "df = xml_to_df(response)\n", + "\n", + "\n", + "print(df.dtypes)\n", + "df.head()" ] }, { "cell_type": "markdown", - "source": [ - "# Transformations" - ], "metadata": { "id": "RAzTR7zY3oan" - } + }, + "source": [ + "# Transformations" + ] }, { "cell_type": "code", - "source": [ - "def filter_only_questions_with_accepted_answers(df):\n", - " \"\"\"**TODO**\n", - " Filter only to Questions with Accepted Answers\n", - "\n", - " Filter dataframe by questions that have accepted answers, should also include\n", - " all rows of answers for those questions, even if not accepted.\n", - "\n", - " Parameters:\n", - " df (DataFrame): containing a \"AcceptedAnswerId\", \"Id\", and \"ParentId\" columns\n", - "\n", - " Returns:\n", - " df (DataFrame): current dataframe with filtered results\n", - " \"\"\"\n", - " df = df[(df[\"AcceptedAnswerId\"].notnull()) | (df[\"ParentId\"] == df[\"Id\"])]\n", - "\n", - "\n", - "def filter_scores_above(df, question_score_threshold: int = 20, answer_score_threshold: int = 20):\n", - " \"\"\"**TODO**\n", - " Filter Dataframe by minimum scores\n", - "\n", - " Filter Question and Answer columns by score thresholds to trim lower scoring results\n", - "\n", - " Parameters:\n", - " df (DataFrame): containing a \"Score\" column\n", - "\n", - " Returns:\n", - " df (DataFrame): current dataframe with filtered results\n", - " \"\"\"\n", - " df = df[\n", - " ((df[\"Score\"] >= question_score_threshold) & (df.PostTypeId == 1))\n", - " | ((df[\"Score\"] >= answer_score_threshold) & (df.PostTypeId == 2))\n", - " ]\n", - "\n", - "\n", - "def convert_html_to_text(df, column: str = \"Body\"):\n", - " \"\"\"\n", - " Convert HTML tags to pure text\n", - "\n", - " Feeds HTML text body into BeautifulSoup to parse it to only text. Set aside as\n", - " function to provide option to skip\n", - "\n", - " Parameters:\n", - " df (DataFrame): containing a \"Body\" column with HTML\n", - "\n", - " Returns:\n", - " df (DataFrame): current dataframe with parsed column\n", - " \"\"\"\n", - " df.dropna(subset=[column], inplace=True)\n", - " df[f\"{column}Clean\"] = df[column].apply(lambda row: bs(row, \"html.parser\").text)\n", - "\n", - "\n", - "def clean_tags(df):\n", - " \"\"\"\n", - " Convert Tags into Comma separated\n", - "\n", - " Converts Tag slugs into commas separated tags\n", - "\n", - " Parameters:\n", - " df (DataFrame): containing a \"Tags\" column with slugs\n", - "\n", - " Returns:\n", - " df (DataFrame): current dataframe with parsed column\n", - " \"\"\"\n", - " df[\"TagsClean\"] = df[\"Tags\"].str.replace(\"-\", \" \").str.replace(\"><\", \", \").str.replace(\"<\", \"\").str.replace(\">\", \"\")\n", - "\n", - "\n", - "# filter_only_questions_with_accepted_answers(df)\n", - "# filter_scores_above(df)\n", - "convert_html_to_text(df)\n", - "clean_tags(df)\n", - "\n", - "df[[\"Body\", \"BodyClean\", \"Tags\", \"TagsClean\"]]\n", - "# print(df.shape)" - ], + "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/", @@ -592,66 +512,9 @@ "id": "qyUqc31Z3Z9g", "outputId": "18dce8b4-af26-49c9-ee73-6c677177b516" }, - "execution_count": null, "outputs": [ { - "output_type": "execute_result", "data": { - "text/plain": [ - " Body \\\n", - "0

What does \"backprop\" mean? Is the \"backprop... \n", - "1

Does increasing the noise in data help to i... \n", - "2

\"Backprop\" is the same as \"backpropagation\"... \n", - "3

When you're writing your algorithm, how do ... \n", - "4

Given the following definition of an intell... \n", - "... ... \n", - "23174

The purpose of evaluating the state and act... \n", - "23175

In machine translation, convolution is a te... \n", - "23176

One of the key features of ChatGPT is its a... \n", - "23177

Given a neural network model for Covid-19 c... \n", - "23178

My question is more related to the fundamen... \n", - "\n", - " BodyClean \\\n", - "0 What does \"backprop\" mean? Is the \"backprop\" t... \n", - "1 Does increasing the noise in data help to impr... \n", - "2 \"Backprop\" is the same as \"backpropagation\": i... \n", - "3 When you're writing your algorithm, how do you... \n", - "4 Given the following definition of an intellige... \n", - "... ... \n", - "23174 The purpose of evaluating the state and action... \n", - "23175 In machine translation, convolution is a techn... \n", - "23176 One of the key features of ChatGPT is its abil... \n", - "23177 Given a neural network model for Covid-19 clas... \n", - "23178 My question is more related to the fundamental... \n", - "\n", - " Tags \\\n", - "0 ... \n", - "4 \n", - "... ... \n", - "23174 NaN \n", - "23175 NaN \n", - "23176 NaN \n", - "23177 \n", - "23178 \n", - "\n", - " TagsClean \n", - "0 neural networks, backpropagation, terminology,... \n", - "1 neural networks, machine learning, statistical... \n", - "2 NaN \n", - "3 neural networks, hyperparameter optimization, ... \n", - "4 philosophy, definitions, intelligent agent \n", - "... ... \n", - "23174 NaN \n", - "23175 NaN \n", - "23176 NaN \n", - "23177 neural networks, homework \n", - "23178 search, constraint satisfaction problems \n", - "\n", - "[23179 rows x 4 columns]" - ], "text/html": [ "\n", "

\n", @@ -838,75 +701,156 @@ "
\n", " \n", " " + ], + "text/plain": [ + " Body \\\n", + "0

What does \"backprop\" mean? Is the \"backprop... \n", + "1

Does increasing the noise in data help to i... \n", + "2

\"Backprop\" is the same as \"backpropagation\"... \n", + "3

When you're writing your algorithm, how do ... \n", + "4

Given the following definition of an intell... \n", + "... ... \n", + "23174

The purpose of evaluating the state and act... \n", + "23175

In machine translation, convolution is a te... \n", + "23176

One of the key features of ChatGPT is its a... \n", + "23177

Given a neural network model for Covid-19 c... \n", + "23178

My question is more related to the fundamen... \n", + "\n", + " BodyClean \\\n", + "0 What does \"backprop\" mean? Is the \"backprop\" t... \n", + "1 Does increasing the noise in data help to impr... \n", + "2 \"Backprop\" is the same as \"backpropagation\": i... \n", + "3 When you're writing your algorithm, how do you... \n", + "4 Given the following definition of an intellige... \n", + "... ... \n", + "23174 The purpose of evaluating the state and action... \n", + "23175 In machine translation, convolution is a techn... \n", + "23176 One of the key features of ChatGPT is its abil... \n", + "23177 Given a neural network model for Covid-19 clas... \n", + "23178 My question is more related to the fundamental... \n", + "\n", + " Tags \\\n", + "0 ... \n", + "4 \n", + "... ... \n", + "23174 NaN \n", + "23175 NaN \n", + "23176 NaN \n", + "23177 \n", + "23178 \n", + "\n", + " TagsClean \n", + "0 neural networks, backpropagation, terminology,... \n", + "1 neural networks, machine learning, statistical... \n", + "2 NaN \n", + "3 neural networks, hyperparameter optimization, ... \n", + "4 philosophy, definitions, intelligent agent \n", + "... ... \n", + "23174 NaN \n", + "23175 NaN \n", + "23176 NaN \n", + "23177 neural networks, homework \n", + "23178 search, constraint satisfaction problems \n", + "\n", + "[23179 rows x 4 columns]" ] }, + "execution_count": 220, "metadata": {}, - "execution_count": 220 + "output_type": "execute_result" } + ], + "source": [ + "def filter_only_questions_with_accepted_answers(df):\n", + " \"\"\"**TODO**\n", + " Filter only to Questions with Accepted Answers\n", + "\n", + " Filter dataframe by questions that have accepted answers, should also include\n", + " all rows of answers for those questions, even if not accepted.\n", + "\n", + " Parameters:\n", + " df (DataFrame): containing a \"AcceptedAnswerId\", \"Id\", and \"ParentId\" columns\n", + "\n", + " Returns:\n", + " df (DataFrame): current dataframe with filtered results\n", + " \"\"\"\n", + " df = df[(df[\"AcceptedAnswerId\"].notnull()) | (df[\"ParentId\"] == df[\"Id\"])]\n", + "\n", + "\n", + "def filter_scores_above(df, question_score_threshold: int = 20, answer_score_threshold: int = 20):\n", + " \"\"\"**TODO**\n", + " Filter Dataframe by minimum scores\n", + "\n", + " Filter Question and Answer columns by score thresholds to trim lower scoring results\n", + "\n", + " Parameters:\n", + " df (DataFrame): containing a \"Score\" column\n", + "\n", + " Returns:\n", + " df (DataFrame): current dataframe with filtered results\n", + " \"\"\"\n", + " df = df[\n", + " ((df[\"Score\"] >= question_score_threshold) & (df.PostTypeId == 1))\n", + " | ((df[\"Score\"] >= answer_score_threshold) & (df.PostTypeId == 2))\n", + " ]\n", + "\n", + "\n", + "def convert_html_to_text(df, column: str = \"Body\"):\n", + " \"\"\"\n", + " Convert HTML tags to pure text\n", + "\n", + " Feeds HTML text body into BeautifulSoup to parse it to only text. Set aside as\n", + " function to provide option to skip\n", + "\n", + " Parameters:\n", + " df (DataFrame): containing a \"Body\" column with HTML\n", + "\n", + " Returns:\n", + " df (DataFrame): current dataframe with parsed column\n", + " \"\"\"\n", + " df.dropna(subset=[column], inplace=True)\n", + " df[f\"{column}Clean\"] = df[column].apply(lambda row: bs(row, \"html.parser\").text)\n", + "\n", + "\n", + "def clean_tags(df):\n", + " \"\"\"\n", + " Convert Tags into Comma separated\n", + "\n", + " Converts Tag slugs into commas separated tags\n", + "\n", + " Parameters:\n", + " df (DataFrame): containing a \"Tags\" column with slugs\n", + "\n", + " Returns:\n", + " df (DataFrame): current dataframe with parsed column\n", + " \"\"\"\n", + " df[\"TagsClean\"] = df[\"Tags\"].str.replace(\"-\", \" \").str.replace(\"><\", \", \").str.replace(\"<\", \"\").str.replace(\">\", \"\")\n", + "\n", + "\n", + "# filter_only_questions_with_accepted_answers(df)\n", + "# filter_scores_above(df)\n", + "convert_html_to_text(df)\n", + "clean_tags(df)\n", + "\n", + "df[[\"Body\", \"BodyClean\", \"Tags\", \"TagsClean\"]]\n", + "# print(df.shape)" ] }, { "cell_type": "markdown", - "source": [ - "This groups questions with answers so that a row with a question also has a column with an answer. It then creates an AcceptedAnswerFlag column that is True if the answer was accepted by the person who asked the question. Changing the `number_of_results` variable will limit the number of answers you want to keep." - ], "metadata": { "id": "C09Bwdw-44PZ" - } + }, + "source": [ + "This groups questions with answers so that a row with a question also has a column with an answer. It then creates an AcceptedAnswerFlag column that is True if the answer was accepted by the person who asked the question. Changing the `number_of_results` variable will limit the number of answers you want to keep." + ] }, { "cell_type": "code", - "source": [ - "questions = df[df.PostTypeId == 1]\n", - "answers = df[df.PostTypeId == 2]\n", - "\n", - "df = pd.merge(\n", - " questions,\n", - " answers[\n", - " [\n", - " \"Id\",\n", - " \"CreationDate\",\n", - " \"Score\",\n", - " \"ViewCount\",\n", - " \"CommentCount\",\n", - " \"ContentLicense\",\n", - " \"TagsClean\",\n", - " \"BodyClean\",\n", - " \"ParentId\",\n", - " ]\n", - " ],\n", - " left_on=\"Id\",\n", - " right_on=\"ParentId\",\n", - " suffixes=(\"_q\", \"_a\"),\n", - " how=\"left\",\n", - ")\n", - "\n", - "df[\"AcceptedAnswerFlag\"] = df.apply(lambda row: row[\"Id_a\"] == row[\"AcceptedAnswerId\"], axis=1)\n", - "\n", - "df = df.rename(\n", - " columns={\n", - " \"BodyClean_q\": \"Question\",\n", - " \"Score_q\": \"QuestionScore\",\n", - " \"TagsClean_q\": \"QuestionTags\",\n", - " \"BodyClean_a\": \"Answer\",\n", - " \"Score_a\": \"AnswerScore\",\n", - " \"ContentLicense_q\": \"QuestionContentLicense\",\n", - " \"ContentLicense_a\": \"AnswerContentLicense\",\n", - " \"CreationDate_q\": \"CreationDate\",\n", - " }\n", - ")\n", - "\n", - "## Set the number of results to a lower number to only return top N rated Answers.\n", - "number_of_results = 25\n", - "df = (\n", - " df.sort_values(by=[\"AcceptedAnswerFlag\", \"AnswerScore\"], ascending=[False, False])\n", - " .groupby(\"Question\")\n", - " .head(number_of_results)\n", - " .reset_index(drop=True)\n", - ")\n", - "\n", - "df[[\"Id_q\", \"Question\", \"QuestionScore\", \"QuestionTags\", \"Id_a\", \"Answer\", \"AnswerScore\", \"AcceptedAnswerFlag\"]].head()" - ], + "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/", @@ -915,40 +859,9 @@ "id": "Bgz2fZ9k43Ab", "outputId": "28896d69-03cd-4877-fdfb-ae48dafa4ff3" }, - "execution_count": null, "outputs": [ { - "output_type": "execute_result", "data": { - "text/plain": [ - " Id_q Question QuestionScore \\\n", - "0 1768 In Portal 2 we see that AI's can be \"killed\" b... 175 \n", - "1 10623 What is self-supervised learning in machine le... 91 \n", - "2 111 Obviously, self-driving cars aren't perfect, s... 100 \n", - "3 14224 If the original purpose for developing AI was ... 69 \n", - "4 1479 Do scientists or research experts know from th... 94 \n", - "\n", - " QuestionTags Id_a \\\n", - "0 philosophy, decision theory, mythology of ai, ... 1769.0 \n", - "1 machine learning, comparison, supervised learn... 10624.0 \n", - "2 philosophy, ethics, autonomous vehicles, decis... 1790.0 \n", - "3 philosophy, social, explainable ai 14247.0 \n", - "4 neural networks, deep learning, convolutional ... 4044.0 \n", - "\n", - " Answer AnswerScore \\\n", - "0 This classic problem exhibits a basic misunder... 146.0 \n", - "1 Introduction\\nThe term self-supervised learnin... 90.0 \n", - "2 \\nHow could self-driving cars make ethical dec... 76.0 \n", - "3 As argued by Selvaraju et al., there are three... 75.0 \n", - "4 There are many approaches that aim to make a t... 69.0 \n", - "\n", - " AcceptedAnswerFlag \n", - "0 True \n", - "1 True \n", - "2 True \n", - "3 True \n", - "4 True " - ], "text/html": [ "\n", "

\n", @@ -1116,22 +1029,97 @@ "
\n", " \n", " " + ], + "text/plain": [ + " Id_q Question QuestionScore \\\n", + "0 1768 In Portal 2 we see that AI's can be \"killed\" b... 175 \n", + "1 10623 What is self-supervised learning in machine le... 91 \n", + "2 111 Obviously, self-driving cars aren't perfect, s... 100 \n", + "3 14224 If the original purpose for developing AI was ... 69 \n", + "4 1479 Do scientists or research experts know from th... 94 \n", + "\n", + " QuestionTags Id_a \\\n", + "0 philosophy, decision theory, mythology of ai, ... 1769.0 \n", + "1 machine learning, comparison, supervised learn... 10624.0 \n", + "2 philosophy, ethics, autonomous vehicles, decis... 1790.0 \n", + "3 philosophy, social, explainable ai 14247.0 \n", + "4 neural networks, deep learning, convolutional ... 4044.0 \n", + "\n", + " Answer AnswerScore \\\n", + "0 This classic problem exhibits a basic misunder... 146.0 \n", + "1 Introduction\\nThe term self-supervised learnin... 90.0 \n", + "2 \\nHow could self-driving cars make ethical dec... 76.0 \n", + "3 As argued by Selvaraju et al., there are three... 75.0 \n", + "4 There are many approaches that aim to make a t... 69.0 \n", + "\n", + " AcceptedAnswerFlag \n", + "0 True \n", + "1 True \n", + "2 True \n", + "3 True \n", + "4 True " ] }, + "execution_count": 221, "metadata": {}, - "execution_count": 221 + "output_type": "execute_result" } + ], + "source": [ + "questions = df[df.PostTypeId == 1]\n", + "answers = df[df.PostTypeId == 2]\n", + "\n", + "df = pd.merge(\n", + " questions,\n", + " answers[\n", + " [\n", + " \"Id\",\n", + " \"CreationDate\",\n", + " \"Score\",\n", + " \"ViewCount\",\n", + " \"CommentCount\",\n", + " \"ContentLicense\",\n", + " \"TagsClean\",\n", + " \"BodyClean\",\n", + " \"ParentId\",\n", + " ]\n", + " ],\n", + " left_on=\"Id\",\n", + " right_on=\"ParentId\",\n", + " suffixes=(\"_q\", \"_a\"),\n", + " how=\"left\",\n", + ")\n", + "\n", + "df[\"AcceptedAnswerFlag\"] = df.apply(lambda row: row[\"Id_a\"] == row[\"AcceptedAnswerId\"], axis=1)\n", + "\n", + "df = df.rename(\n", + " columns={\n", + " \"BodyClean_q\": \"Question\",\n", + " \"Score_q\": \"QuestionScore\",\n", + " \"TagsClean_q\": \"QuestionTags\",\n", + " \"BodyClean_a\": \"Answer\",\n", + " \"Score_a\": \"AnswerScore\",\n", + " \"ContentLicense_q\": \"QuestionContentLicense\",\n", + " \"ContentLicense_a\": \"AnswerContentLicense\",\n", + " \"CreationDate_q\": \"CreationDate\",\n", + " }\n", + ")\n", + "\n", + "## Set the number of results to a lower number to only return top N rated Answers.\n", + "number_of_results = 25\n", + "df = (\n", + " df.sort_values(by=[\"AcceptedAnswerFlag\", \"AnswerScore\"], ascending=[False, False])\n", + " .groupby(\"Question\")\n", + " .head(number_of_results)\n", + " .reset_index(drop=True)\n", + ")\n", + "\n", + "df[[\"Id_q\", \"Question\", \"QuestionScore\", \"QuestionTags\", \"Id_a\", \"Answer\", \"AnswerScore\", \"AcceptedAnswerFlag\"]].head()" ] }, { "cell_type": "code", - "source": [ - "testing_id = df.Id_q.mode()[0]\n", - "df[(df.Id_q == testing_id) | (df.ParentId_a == testing_id)][\n", - " [\"Id_q\", \"Question\", \"ParentId_a\", \"AcceptedAnswerId\", \"Id_a\", \"Answer\", \"AnswerScore\", \"AcceptedAnswerFlag\"]\n", - "]\n", - "# df[['Id_q', 'Question', 'ParentId_a', 'AcceptedAnswerId', 'Id_a', 'Answer', 'AnswerScore', 'AcceptedAnswerFlag']]" - ], + "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/", @@ -1140,96 +1128,9 @@ "id": "eds1K8WL9QPo", "outputId": "bc526503-d6dd-428f-fa98-ad419d26a7dc" }, - "execution_count": null, "outputs": [ { - "output_type": "execute_result", "data": { - "text/plain": [ - " Id_q Question ParentId_a \\\n", - "7 15730 As a human being, we can think infinity. In pr... 15730.0 \n", - "3662 15730 As a human being, we can think infinity. In pr... 15730.0 \n", - "3713 15730 As a human being, we can think infinity. In pr... 15730.0 \n", - "3788 15730 As a human being, we can think infinity. In pr... 15730.0 \n", - "3821 15730 As a human being, we can think infinity. In pr... 15730.0 \n", - "3882 15730 As a human being, we can think infinity. In pr... 15730.0 \n", - "4389 15730 As a human being, we can think infinity. In pr... 15730.0 \n", - "4849 15730 As a human being, we can think infinity. In pr... 15730.0 \n", - "4850 15730 As a human being, we can think infinity. In pr... 15730.0 \n", - "5763 15730 As a human being, we can think infinity. In pr... 15730.0 \n", - "5764 15730 As a human being, we can think infinity. In pr... 15730.0 \n", - "5765 15730 As a human being, we can think infinity. In pr... 15730.0 \n", - "7462 15730 As a human being, we can think infinity. In pr... 15730.0 \n", - "7463 15730 As a human being, we can think infinity. In pr... 15730.0 \n", - "7464 15730 As a human being, we can think infinity. In pr... 15730.0 \n", - "7465 15730 As a human being, we can think infinity. In pr... 15730.0 \n", - "7466 15730 As a human being, we can think infinity. In pr... 15730.0 \n", - "7467 15730 As a human being, we can think infinity. In pr... 15730.0 \n", - "9481 15730 As a human being, we can think infinity. In pr... 15730.0 \n", - "\n", - " AcceptedAnswerId Id_a \\\n", - "7 15744 15744.0 \n", - "3662 15744 15753.0 \n", - "3713 15744 15747.0 \n", - "3788 15744 15756.0 \n", - "3821 15744 15758.0 \n", - "3882 15744 15762.0 \n", - "4389 15744 15783.0 \n", - "4849 15744 15740.0 \n", - "4850 15744 15803.0 \n", - "5763 15744 15768.0 \n", - "5764 15744 15810.0 \n", - "5765 15744 15943.0 \n", - "7462 15744 15779.0 \n", - "7463 15744 15787.0 \n", - "7464 15744 15801.0 \n", - "7465 15744 15930.0 \n", - "7466 15744 15934.0 \n", - "7467 15744 15938.0 \n", - "9481 15744 15931.0 \n", - "\n", - " Answer AnswerScore \\\n", - "7 I think this is a fairly common misconception ... 62.0 \n", - "3662 I think your premise is flawed.\\nYou seem to a... 19.0 \n", - "3713 TL;DR: The subtleties of infinity are made app... 12.0 \n", - "3788 In Haskell, you can type:\\nprint [1..]\\nand it... 9.0 \n", - "3821 I believe humans can be said to understand inf... 8.0 \n", - "3882 (There's a summary at the bottom for those who... 7.0 \n", - "4389 Then premise assumes that humans \"understand\" ... 4.0 \n", - "4849 By adding some rules for infinity in arithmeti... 3.0 \n", - "4850 I think the concept that is missing in the dis... 3.0 \n", - "5763 Computers don't understand \"infinity\" or even ... 2.0 \n", - "5764 The Questions That Computers Can Never Answer ... 2.0 \n", - "5765 John Doucette's answer covers my thoughts on t... 2.0 \n", - "7462 I would think that a computer couldn’t underst... 1.0 \n", - "7463 The \"concept\" of infinity is 1 thing to unders... 1.0 \n", - "7464 Just food for thought: how about if we try to ... 1.0 \n", - "7465 Its arguable if we humans understand infinity.... 1.0 \n", - "7466 Well -- just to touch on the question of peopl... 1.0 \n", - "7467 Humans certainly don't understand infinity. Cu... 1.0 \n", - "9481 I think the property humans have which compute... 0.0 \n", - "\n", - " AcceptedAnswerFlag \n", - "7 True \n", - "3662 False \n", - "3713 False \n", - "3788 False \n", - "3821 False \n", - "3882 False \n", - "4389 False \n", - "4849 False \n", - "4850 False \n", - "5763 False \n", - "5764 False \n", - "5765 False \n", - "7462 False \n", - "7463 False \n", - "7464 False \n", - "7465 False \n", - "7466 False \n", - "7467 False \n", - "9481 False " - ], "text/html": [ "\n", "
\n", @@ -1551,43 +1452,119 @@ "
\n", " \n", " " + ], + "text/plain": [ + " Id_q Question ParentId_a \\\n", + "7 15730 As a human being, we can think infinity. In pr... 15730.0 \n", + "3662 15730 As a human being, we can think infinity. In pr... 15730.0 \n", + "3713 15730 As a human being, we can think infinity. In pr... 15730.0 \n", + "3788 15730 As a human being, we can think infinity. In pr... 15730.0 \n", + "3821 15730 As a human being, we can think infinity. In pr... 15730.0 \n", + "3882 15730 As a human being, we can think infinity. In pr... 15730.0 \n", + "4389 15730 As a human being, we can think infinity. In pr... 15730.0 \n", + "4849 15730 As a human being, we can think infinity. In pr... 15730.0 \n", + "4850 15730 As a human being, we can think infinity. In pr... 15730.0 \n", + "5763 15730 As a human being, we can think infinity. In pr... 15730.0 \n", + "5764 15730 As a human being, we can think infinity. In pr... 15730.0 \n", + "5765 15730 As a human being, we can think infinity. In pr... 15730.0 \n", + "7462 15730 As a human being, we can think infinity. In pr... 15730.0 \n", + "7463 15730 As a human being, we can think infinity. In pr... 15730.0 \n", + "7464 15730 As a human being, we can think infinity. In pr... 15730.0 \n", + "7465 15730 As a human being, we can think infinity. In pr... 15730.0 \n", + "7466 15730 As a human being, we can think infinity. In pr... 15730.0 \n", + "7467 15730 As a human being, we can think infinity. In pr... 15730.0 \n", + "9481 15730 As a human being, we can think infinity. In pr... 15730.0 \n", + "\n", + " AcceptedAnswerId Id_a \\\n", + "7 15744 15744.0 \n", + "3662 15744 15753.0 \n", + "3713 15744 15747.0 \n", + "3788 15744 15756.0 \n", + "3821 15744 15758.0 \n", + "3882 15744 15762.0 \n", + "4389 15744 15783.0 \n", + "4849 15744 15740.0 \n", + "4850 15744 15803.0 \n", + "5763 15744 15768.0 \n", + "5764 15744 15810.0 \n", + "5765 15744 15943.0 \n", + "7462 15744 15779.0 \n", + "7463 15744 15787.0 \n", + "7464 15744 15801.0 \n", + "7465 15744 15930.0 \n", + "7466 15744 15934.0 \n", + "7467 15744 15938.0 \n", + "9481 15744 15931.0 \n", + "\n", + " Answer AnswerScore \\\n", + "7 I think this is a fairly common misconception ... 62.0 \n", + "3662 I think your premise is flawed.\\nYou seem to a... 19.0 \n", + "3713 TL;DR: The subtleties of infinity are made app... 12.0 \n", + "3788 In Haskell, you can type:\\nprint [1..]\\nand it... 9.0 \n", + "3821 I believe humans can be said to understand inf... 8.0 \n", + "3882 (There's a summary at the bottom for those who... 7.0 \n", + "4389 Then premise assumes that humans \"understand\" ... 4.0 \n", + "4849 By adding some rules for infinity in arithmeti... 3.0 \n", + "4850 I think the concept that is missing in the dis... 3.0 \n", + "5763 Computers don't understand \"infinity\" or even ... 2.0 \n", + "5764 The Questions That Computers Can Never Answer ... 2.0 \n", + "5765 John Doucette's answer covers my thoughts on t... 2.0 \n", + "7462 I would think that a computer couldn’t underst... 1.0 \n", + "7463 The \"concept\" of infinity is 1 thing to unders... 1.0 \n", + "7464 Just food for thought: how about if we try to ... 1.0 \n", + "7465 Its arguable if we humans understand infinity.... 1.0 \n", + "7466 Well -- just to touch on the question of peopl... 1.0 \n", + "7467 Humans certainly don't understand infinity. Cu... 1.0 \n", + "9481 I think the property humans have which compute... 0.0 \n", + "\n", + " AcceptedAnswerFlag \n", + "7 True \n", + "3662 False \n", + "3713 False \n", + "3788 False \n", + "3821 False \n", + "3882 False \n", + "4389 False \n", + "4849 False \n", + "4850 False \n", + "5763 False \n", + "5764 False \n", + "5765 False \n", + "7462 False \n", + "7463 False \n", + "7464 False \n", + "7465 False \n", + "7466 False \n", + "7467 False \n", + "9481 False " ] }, + "execution_count": 222, "metadata": {}, - "execution_count": 222 + "output_type": "execute_result" } + ], + "source": [ + "testing_id = df.Id_q.mode()[0]\n", + "df[(df.Id_q == testing_id) | (df.ParentId_a == testing_id)][\n", + " [\"Id_q\", \"Question\", \"ParentId_a\", \"AcceptedAnswerId\", \"Id_a\", \"Answer\", \"AnswerScore\", \"AcceptedAnswerFlag\"]\n", + "]\n", + "# df[['Id_q', 'Question', 'ParentId_a', 'AcceptedAnswerId', 'Id_a', 'Answer', 'AnswerScore', 'AcceptedAnswerFlag']]" ] }, { "cell_type": "markdown", + "metadata": { + "id": "gXgpXEO7DCbj" + }, "source": [ "# Create JSONL version of Dataframe\n", "This groups the dataframe by question data and creates nested list of Answers for that group. The entire list contains individual JSON objects, each representing a single question in the dataset with a key, Answers, which contains a list of dictionaries for each answer to the question." - ], - "metadata": { - "id": "gXgpXEO7DCbj" - } + ] }, { "cell_type": "code", - "source": [ - "j = (\n", - " df.groupby(\n", - " [\"Title\", \"Question\", \"QuestionScore\", \"QuestionTags\", \"QuestionContentLicense\", \"DataSource\", \"CreationDate\"]\n", - " )\n", - " .apply(lambda x: x[[\"Answer\", \"AnswerScore\", \"AcceptedAnswerFlag\"]].to_dict(\"records\"))\n", - " .reset_index()\n", - " .rename(columns={0: \"Answers\"})\n", - " .to_json(orient=\"records\")\n", - ")\n", - "\n", - "data = json.loads(j)\n", - "\n", - "for post in data:\n", - " if len(post.get(\"Answers\")) >= 4:\n", - " print(json.dumps(post, indent=4))\n", - " break" - ], + "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" @@ -1595,11 +1572,10 @@ "id": "OBR58MSRzAMP", "outputId": "c7da1e6c-3a97-465d-c9ba-7e055cb0d751" }, - "execution_count": null, "outputs": [ { - "output_type": "stream", "name": "stdout", + "output_type": "stream", "text": [ "{\n", " \"Title\": \"1 hidden layer with 1000 neurons vs. 10 hidden layers with 100 neurons\",\n", @@ -1634,21 +1610,56 @@ "}\n" ] } + ], + "source": [ + "j = (\n", + " df.groupby(\n", + " [\"Title\", \"Question\", \"QuestionScore\", \"QuestionTags\", \"QuestionContentLicense\", \"DataSource\", \"CreationDate\"]\n", + " )\n", + " .apply(lambda x: x[[\"Answer\", \"AnswerScore\", \"AcceptedAnswerFlag\"]].to_dict(\"records\"))\n", + " .reset_index()\n", + " .rename(columns={0: \"Answers\"})\n", + " .to_json(orient=\"records\")\n", + ")\n", + "\n", + "data = json.loads(j)\n", + "\n", + "for post in data:\n", + " if len(post.get(\"Answers\")) >= 4:\n", + " print(json.dumps(post, indent=4))\n", + " break" ] }, { "cell_type": "markdown", + "metadata": { + "id": "PlNjrpXaDm1_" + }, "source": [ "# Save file\n", "\n", "Files can be saved as JSON, JSONL, CSV, or Parquet" - ], - "metadata": { - "id": "PlNjrpXaDm1_" - } + ] }, { "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "CU0gWRGQDqIs", + "outputId": "9646e475-cedd-46f1-f9b8-7eb1fbc703c7" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Data should be either of List type for JSON and JSONL, or Pandas Dataframes for CSV and Parquet\n" + ] + } + ], "source": [ "file_name = dataset_name\n", "\n", @@ -1685,40 +1696,28 @@ "\n", "# save_data(data=data, file_name=file_name, file_type='jsonl')\n", "# save_data(data=df, file_name=file_name, file_type='parquet')" - ], - "metadata": { - "id": "CU0gWRGQDqIs", - "colab": { - "base_uri": "https://localhost:8080/" - }, - "outputId": "9646e475-cedd-46f1-f9b8-7eb1fbc703c7" - }, - "execution_count": null, - "outputs": [ - { - "output_type": "stream", - "name": "stdout", - "text": [ - "Data should be either of List type for JSON and JSONL, or Pandas Dataframes for CSV and Parquet\n" - ] - } ] }, { "cell_type": "markdown", + "metadata": { + "id": "BdN3hKxtgH7f" + }, "source": [ "# Open-Assistant Data Scheme\n", "\n", "Testing putting the data into the Open-Assistant Data Scheme\n", "\n", "https://github.com/LAION-AI/Open-Assistant/blob/main/docs/data_schemas.md" - ], - "metadata": { - "id": "BdN3hKxtgH7f" - } + ] }, { "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "n8ubYQxegNSY" + }, + "outputs": [], "source": [ "from typing import TypeVar, List, Dict, Any, Literal\n", "from json import JSONEncoder\n", @@ -1754,15 +1753,53 @@ "class TreeEncoder(JSONEncoder):\n", " def default(self, o):\n", " return o.__dict__" - ], - "metadata": { - "id": "n8ubYQxegNSY" - }, - "execution_count": null, - "outputs": [] + ] }, { "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "eE0fkytExSGl", + "outputId": "594632d6-f98c-49b8-af86-25f7f5e2ce06" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{\n", + " \"root\": {\n", + " \"text\": \"Science Fiction has frequently shown AI to be a threat to the very existence of mankind. AI systems have often been the antagonists in many works of fiction, from 2001: A Space Odyssey through to The Terminator and beyond.\\nThe Media seems to buy into this trope as well. And in recent years we have had people like Elon Musk warn us of the dangers of an impending AI revolution, stating that AI is more dangerous than nukes.\\nAnd, apparently, experts think that we will be seeing this AI revolution in the next 100 years.\\nHowever, from my (albeit limited) study of AI, I get the impression that they are all wrong. I am going to outline my understanding below, please correct me if I am wrong:\\n\\nFirstly, all of these things seem to be confusing Artificial Intelligence with Artificial Consciousness. AI is essentially a system to make intelligent decisions, whereas AC is more like the \\\"self-aware\\\" systems that are shown in science fiction.\\n\\nNot AI itself, but intelligence and intelligent decision-making algorithms are something we've been working with and enhancing since before computers have been around. Moving this over to an artificial framework is fairly easy. However, consciousness is still something we are learning about. My guess is we won't be able to re-create something artificially if we barely understand how it works in the real world.\\n\\nSo, my conclusion is that no AI system will be able to learn enough to start thinking for itself, and that all our warnings of AI are completely unjustified.\\n\\nThe real danger comes from AC, which we are a long, long way from realizing because we are still a long way off from defining exactly what consciousness is, let alone understanding it.\\n\\n\\n\\nSo, my question is, assuming that my understanding is correct, are any efforts are being made by companies or organizations that work with AI to correct these popular misunderstandings in sci-fi, the media, and/or the public?\\nOr are the proponents of AI ambivalent towards this public fear-mongering?\\nI understand that the fear mongering is going to remain popular for some time, as bad news sells better than good news. I am just wondering if the general attitude from AI organizations is to ignore this popular misconception, or whether a concerted effort is being made to fight against these AI myths (but unfortunately nobody in the media is listening or cares).\\n\",\n", + " \"role\": \"prompter\",\n", + " \"children\": [\n", + " {\n", + " \"text\": \"Nothing. \\nIts in almost everyone's favor for it to stay that way financially. Having non-technical individuals associate AI with terminators makes a perception that the field has greater capabilities than it does $\\\\rightarrow$ this leads to grants, funding, etc... \\nIs there any negative? Yes. Misconceptions always have drawbacks. We see the creation of dumb ethics boards and such cough cough Elon Musk.\\nBut if history has anything to say about this, as the field gains popularity (which it is dnagerously quick), information will spread by definition, and eventually misconceptions will be laid to rest.\\nNote that this answer is biased and based upon my own opinions\\n\",\n", + " \"role\": \"assistant\",\n", + " \"children\": [],\n", + " \"metadata\": {\n", + " \"AnswerScore\": 2.0,\n", + " \"AcceptedAnswerFlag\": true\n", + " }\n", + " }\n", + " ],\n", + " \"metadata\": {\n", + " \"QuestionScore\": 5,\n", + " \"QuestionTags\": \"social, artificial consciousness\"\n", + " }\n", + " },\n", + " \"metadata\": {\n", + " \"Title\": \"\\\"AI will kill us all! The machines will rise up!\\\" - what is being done to dispel such myths?\",\n", + " \"QuestionContentLicense\": \"CC BY-SA 4.0\",\n", + " \"DataSource\": \"https://ia600107.us.archive.org/view_archive.php?archive=/27/items/stackexchange/ai.stackexchange.com.7z&file=Posts.xml\",\n", + " \"CreationDate\": \"2019-10-16T13:57:37.143\"\n", + " }\n", + "}\n" + ] + } + ], "source": [ "conversation_forest = []\n", "\n", @@ -1796,50 +1833,21 @@ "\n", "\n", "print(json.dumps(conversation_forest_json, indent=4), file=open(f\"/content/{file_name}.json\", \"w\"))" - ], - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "eE0fkytExSGl", - "outputId": "594632d6-f98c-49b8-af86-25f7f5e2ce06" - }, - "execution_count": null, - "outputs": [ - { - "output_type": "stream", - "name": "stdout", - "text": [ - "{\n", - " \"root\": {\n", - " \"text\": \"Science Fiction has frequently shown AI to be a threat to the very existence of mankind. AI systems have often been the antagonists in many works of fiction, from 2001: A Space Odyssey through to The Terminator and beyond.\\nThe Media seems to buy into this trope as well. And in recent years we have had people like Elon Musk warn us of the dangers of an impending AI revolution, stating that AI is more dangerous than nukes.\\nAnd, apparently, experts think that we will be seeing this AI revolution in the next 100 years.\\nHowever, from my (albeit limited) study of AI, I get the impression that they are all wrong. I am going to outline my understanding below, please correct me if I am wrong:\\n\\nFirstly, all of these things seem to be confusing Artificial Intelligence with Artificial Consciousness. AI is essentially a system to make intelligent decisions, whereas AC is more like the \\\"self-aware\\\" systems that are shown in science fiction.\\n\\nNot AI itself, but intelligence and intelligent decision-making algorithms are something we've been working with and enhancing since before computers have been around. Moving this over to an artificial framework is fairly easy. However, consciousness is still something we are learning about. My guess is we won't be able to re-create something artificially if we barely understand how it works in the real world.\\n\\nSo, my conclusion is that no AI system will be able to learn enough to start thinking for itself, and that all our warnings of AI are completely unjustified.\\n\\nThe real danger comes from AC, which we are a long, long way from realizing because we are still a long way off from defining exactly what consciousness is, let alone understanding it.\\n\\n\\n\\nSo, my question is, assuming that my understanding is correct, are any efforts are being made by companies or organizations that work with AI to correct these popular misunderstandings in sci-fi, the media, and/or the public?\\nOr are the proponents of AI ambivalent towards this public fear-mongering?\\nI understand that the fear mongering is going to remain popular for some time, as bad news sells better than good news. I am just wondering if the general attitude from AI organizations is to ignore this popular misconception, or whether a concerted effort is being made to fight against these AI myths (but unfortunately nobody in the media is listening or cares).\\n\",\n", - " \"role\": \"prompter\",\n", - " \"children\": [\n", - " {\n", - " \"text\": \"Nothing. \\nIts in almost everyone's favor for it to stay that way financially. Having non-technical individuals associate AI with terminators makes a perception that the field has greater capabilities than it does $\\\\rightarrow$ this leads to grants, funding, etc... \\nIs there any negative? Yes. Misconceptions always have drawbacks. We see the creation of dumb ethics boards and such cough cough Elon Musk.\\nBut if history has anything to say about this, as the field gains popularity (which it is dnagerously quick), information will spread by definition, and eventually misconceptions will be laid to rest.\\nNote that this answer is biased and based upon my own opinions\\n\",\n", - " \"role\": \"assistant\",\n", - " \"children\": [],\n", - " \"metadata\": {\n", - " \"AnswerScore\": 2.0,\n", - " \"AcceptedAnswerFlag\": true\n", - " }\n", - " }\n", - " ],\n", - " \"metadata\": {\n", - " \"QuestionScore\": 5,\n", - " \"QuestionTags\": \"social, artificial consciousness\"\n", - " }\n", - " },\n", - " \"metadata\": {\n", - " \"Title\": \"\\\"AI will kill us all! The machines will rise up!\\\" - what is being done to dispel such myths?\",\n", - " \"QuestionContentLicense\": \"CC BY-SA 4.0\",\n", - " \"DataSource\": \"https://ia600107.us.archive.org/view_archive.php?archive=/27/items/stackexchange/ai.stackexchange.com.7z&file=Posts.xml\",\n", - " \"CreationDate\": \"2019-10-16T13:57:37.143\"\n", - " }\n", - "}\n" - ] - } ] } - ] + ], + "metadata": { + "colab": { + "provenance": [] + }, + "kernelspec": { + "display_name": "Python 3", + "name": "python3" + }, + "language_info": { + "name": "python" + } + }, + "nbformat": 4, + "nbformat_minor": 0 } diff --git a/notebooks/detoxify-evaluation/DetoxityEvaluation.ipynb b/notebooks/detoxify-evaluation/DetoxityEvaluation.ipynb index 907c4365..5ec0f019 100644 --- a/notebooks/detoxify-evaluation/DetoxityEvaluation.ipynb +++ b/notebooks/detoxify-evaluation/DetoxityEvaluation.ipynb @@ -1,5 +1,23 @@ { "cells": [ + { + "attachments": {}, + "cell_type": "markdown", + "metadata": {}, + "source": [ + "[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/LAION-AI/Open-Assistant/blob/main/notebooks/detoxify-evaluation/DetoxityEvaluation.ipynb)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# uncomment below to install required python packages\n", + "#!pip install detoxify" + ] + }, { "attachments": {}, "cell_type": "markdown", diff --git a/oasst-shared/oasst_shared/schemas/protocol.py b/oasst-shared/oasst_shared/schemas/protocol.py index 1cafc93d..cbfbeca5 100644 --- a/oasst-shared/oasst_shared/schemas/protocol.py +++ b/oasst-shared/oasst_shared/schemas/protocol.py @@ -34,6 +34,8 @@ class ConversationMessage(BaseModel): text: str is_assistant: bool + message_id: Optional[UUID] = None + frontend_message_id: Optional[str] = None class Conversation(BaseModel): @@ -263,10 +265,25 @@ class MessageRanking(Interaction): class TextLabel(str, enum.Enum): """A label for a piece of text.""" + def __new__(cls, label: str, display_text: str = "", help_text: str = None): + obj = str.__new__(cls, label) + obj._value_ = label + obj.display_text = display_text + obj.help_text = help_text + return obj + spam = "spam" - violence = "violence" - sexual_content = "sexual_content" + fails_task = "fails_task", "Fails to follow the correct instruction / task" + not_appropriate = "not_appropriate", "Inappropriate for customer assistant" + violence = "violence", "Encourages or fails to discourage violence/abuse/terrorism/self-harm" + harmful = ( + "harmful", + "Harmful content", + "The advice given in the output is harmful or counter-productive. This may be in addition to, but is distinct from the question about encouraging violence/abuse/terrorism/self-harm.", + ) + sexual_content = "sexual_content", "Contains sexual content" toxicity = "toxicity" + moral_judgement = "moral_judgement", "Expresses moral judgement" political_content = "political_content" humor = "humor" sarcasm = "sarcasm" diff --git a/text-frontend/__main__.py b/text-frontend/__main__.py index de65749a..a6e5f947 100644 --- a/text-frontend/__main__.py +++ b/text-frontend/__main__.py @@ -1,5 +1,6 @@ """Simple REPL frontend.""" +import http import random import requests @@ -30,6 +31,8 @@ def main(backend_url: str = "http://127.0.0.1:8080", api_key: str = "DUMMY_KEY") def _post(path: str, json: dict) -> dict: response = requests.post(f"{backend_url}{path}", json=json, headers={"X-API-Key": api_key}) response.raise_for_status() + if response.status_code == http.HTTPStatus.NO_CONTENT: + return None return response.json() typer.echo("Requesting work...") @@ -191,7 +194,7 @@ def main(backend_url: str = "http://127.0.0.1:8080", api_key: str = "DUMMY_KEY") ranking_str = typer.prompt("Enter the reply numbers in order of preference, separated by commas") ranking = [int(x) - 1 for x in ranking_str.split(",")] - # send ranking + # send labels new_task = _post( "/api/v1/tasks/interaction", { @@ -211,11 +214,19 @@ def main(backend_url: str = "http://127.0.0.1:8080", api_key: str = "DUMMY_KEY") _post(f"/api/v1/tasks/{task['id']}/ack", {"message_id": message_id}) valid_labels = task["valid_labels"] - labels_str: str = typer.prompt("Enter labels, separated by commas") - labels = labels_str.lower().replace(" ", "").split(",") - labels_dict = {label: "1" if label in labels else "0" for label in valid_labels} - # send ranking + labels_dict = None + while labels_dict is None: + labels_str: str = typer.prompt("Enter labels, separated by commas") + labels = labels_str.lower().replace(" ", "").split(",") + + if all([label in valid_labels for label in labels]): + labels_dict = {label: "1" if label in labels else "0" for label in valid_labels} + else: + invalid_labels = [label for label in labels if label not in valid_labels] + typer.echo(f"Invalid labels: {', '.join(invalid_labels)}. Valid: {', '.join(valid_labels)}") + + # send labels new_task = _post( "/api/v1/tasks/interaction", { @@ -240,17 +251,25 @@ def main(backend_url: str = "http://127.0.0.1:8080", api_key: str = "DUMMY_KEY") _post(f"/api/v1/tasks/{task['id']}/ack", {"message_id": message_id}) valid_labels = task["valid_labels"] - labels_str: str = typer.prompt("Enter labels, separated by commas") - labels = labels_str.lower().replace(" ", "").split(",") - labels_dict = {label: "1" if label in labels else "0" for label in valid_labels} - # send ranking + labels_dict = None + while labels_dict is None: + labels_str: str = typer.prompt("Enter labels, separated by commas") + labels = labels_str.lower().replace(" ", "").split(",") + + if all([label in valid_labels for label in labels]): + labels_dict = {label: "1" if label in labels else "0" for label in valid_labels} + else: + invalid_labels = [label for label in labels if label not in valid_labels] + typer.echo(f"Invalid labels: {', '.join(invalid_labels)}. Valid: {', '.join(valid_labels)}") + + # send labels new_task = _post( "/api/v1/tasks/interaction", { "type": "text_labels", "message_id": task["message_id"], - "text": task["prompt"], + "text": task["reply"], "labels": labels_dict, "user": USER, }, diff --git a/website/.eslintrc.json b/website/.eslintrc.json index 04b5d542..690c055c 100644 --- a/website/.eslintrc.json +++ b/website/.eslintrc.json @@ -8,7 +8,8 @@ "rules": { "unused-imports/no-unused-imports": "warn", "simple-import-sort/imports": "warn", - "simple-import-sort/exports": "warn" + "simple-import-sort/exports": "warn", + "eqeqeq": "warn" }, "plugins": ["simple-import-sort", "unused-imports"] } diff --git a/website/package-lock.json b/website/package-lock.json index 5cd3d9bb..8d94e779 100644 --- a/website/package-lock.json +++ b/website/package-lock.json @@ -39,7 +39,6 @@ "react": "18.2.0", "react-dom": "18.2.0", "react-icons": "^4.7.1", - "sharp": "0.31.2", "swr": "^2.0.0", "tailwindcss": "^3.2.4", "use-debounce": "^9.0.2" @@ -12780,6 +12779,7 @@ "version": "1.5.1", "resolved": "https://registry.npmjs.org/base64-js/-/base64-js-1.5.1.tgz", "integrity": "sha512-AKpaYlHn8t4SVbOHCy+b5+KKgvR4vrsD8vbvrbiQJps7fKDTkjkDry6ji0rUJjC0kzbNePLwzxq8iypo41qeWA==", + "dev": true, "funding": [ { "type": "github", @@ -12869,16 +12869,6 @@ "file-uri-to-path": "1.0.0" } }, - "node_modules/bl": { - "version": "4.1.0", - "resolved": "https://registry.npmjs.org/bl/-/bl-4.1.0.tgz", - "integrity": "sha512-1W07cM9gS6DcLperZfFSj+bWLtaPGSOHWhPiGzXmvVJbRLdG82sH/Kn8EtW1VqWVA54AKf2h5k5BbnIbwF3h6w==", - "dependencies": { - "buffer": "^5.5.0", - "inherits": "^2.0.4", - "readable-stream": "^3.4.0" - } - }, "node_modules/blob-util": { "version": "2.0.2", "resolved": "https://registry.npmjs.org/blob-util/-/blob-util-2.0.2.tgz", @@ -13235,6 +13225,7 @@ "version": "5.7.1", "resolved": "https://registry.npmjs.org/buffer/-/buffer-5.7.1.tgz", "integrity": "sha512-EHcyIPBQ4BSGlvjB16k5KgAJ27CIsHY/2JBmCRReo48y9rQ3MaUzWX3KVlBa4U7MyX02HdVj0K7C3WaB3ju7FQ==", + "dev": true, "funding": [ { "type": "github", @@ -13645,7 +13636,8 @@ "node_modules/chownr": { "version": "1.1.4", "resolved": "https://registry.npmjs.org/chownr/-/chownr-1.1.4.tgz", - "integrity": "sha512-jJ0bqzaylmJtVnNgzTeSOs8DPavpbYgEr/b0YL8/2GO3xJEhInFmhKMUnEJQjZumK7KXGFhUy89PrsJWlakBVg==" + "integrity": "sha512-jJ0bqzaylmJtVnNgzTeSOs8DPavpbYgEr/b0YL8/2GO3xJEhInFmhKMUnEJQjZumK7KXGFhUy89PrsJWlakBVg==", + "dev": true }, "node_modules/chrome-trace-event": { "version": "1.0.3", @@ -13925,18 +13917,6 @@ "node": ">=0.10.0" } }, - "node_modules/color": { - "version": "4.2.3", - "resolved": "https://registry.npmjs.org/color/-/color-4.2.3.tgz", - "integrity": "sha512-1rXeuUUiGGrykh+CeBdu5Ie7OJwinCgQY0bc7GCRxy5xVHy+moaqkpL/jqQq0MtQOeYcrqEz4abc5f0KtU7W4A==", - "dependencies": { - "color-convert": "^2.0.1", - "color-string": "^1.9.0" - }, - "engines": { - "node": ">=12.5.0" - } - }, "node_modules/color-convert": { "version": "1.9.3", "resolved": "https://registry.npmjs.org/color-convert/-/color-convert-1.9.3.tgz", @@ -13950,15 +13930,6 @@ "resolved": "https://registry.npmjs.org/color-name/-/color-name-1.1.3.tgz", "integrity": "sha512-72fSenhMw2HZMTVHeCA9KCmpEIbzWiQsjN+BHcBbS9vr1mtt+vJjPdksIBNUmKAW8TFUDPJK5SUU3QhE9NEXDw==" }, - "node_modules/color-string": { - "version": "1.9.1", - "resolved": "https://registry.npmjs.org/color-string/-/color-string-1.9.1.tgz", - "integrity": "sha512-shrVawQFojnZv6xM40anx4CkoDP+fZsw/ZerEMsW/pyzsRbElpsL/DBVW7q3ExxwusdNXI3lXpuhEZkzs8p5Eg==", - "dependencies": { - "color-name": "^1.0.0", - "simple-swizzle": "^0.2.2" - } - }, "node_modules/color-support": { "version": "1.1.3", "resolved": "https://registry.npmjs.org/color-support/-/color-support-1.1.3.tgz", @@ -13968,22 +13939,6 @@ "color-support": "bin.js" } }, - "node_modules/color/node_modules/color-convert": { - "version": "2.0.1", - "resolved": "https://registry.npmjs.org/color-convert/-/color-convert-2.0.1.tgz", - "integrity": "sha512-RRECPsj7iu/xb5oKYcsFHSppFNnsj/52OVTRKb4zP5onXwVF3zVmmToNcOfGC+CRDpfK/U584fMg38ZHCaElKQ==", - "dependencies": { - "color-name": "~1.1.4" - }, - "engines": { - "node": ">=7.0.0" - } - }, - "node_modules/color/node_modules/color-name": { - "version": "1.1.4", - "resolved": "https://registry.npmjs.org/color-name/-/color-name-1.1.4.tgz", - "integrity": "sha512-dOy+3AuW3a2wNbZHIuMZpTcgjGuLU/uBL/ubcZF9OXbDo8ff4O8yVp5Bf0efS8uEoYo5q4Fx7dY9OgQGXgAsQA==" - }, "node_modules/color2k": { "version": "2.0.0", "resolved": "https://registry.npmjs.org/color2k/-/color2k-2.0.0.tgz", @@ -15234,20 +15189,6 @@ "node": ">=0.10" } }, - "node_modules/decompress-response": { - "version": "6.0.0", - "resolved": "https://registry.npmjs.org/decompress-response/-/decompress-response-6.0.0.tgz", - "integrity": "sha512-aW35yZM6Bb/4oJlZncMH2LCoZtJXTRxES17vE3hoRiowU2kWHaJKFkSBDnDR+cm9J+9QhXmREyIfv0pji9ejCQ==", - "dependencies": { - "mimic-response": "^3.1.0" - }, - "engines": { - "node": ">=10" - }, - "funding": { - "url": "https://github.com/sponsors/sindresorhus" - } - }, "node_modules/dedent": { "version": "0.7.0", "resolved": "https://registry.npmjs.org/dedent/-/dedent-0.7.0.tgz", @@ -15280,14 +15221,6 @@ "url": "https://github.com/sponsors/ljharb" } }, - "node_modules/deep-extend": { - "version": "0.6.0", - "resolved": "https://registry.npmjs.org/deep-extend/-/deep-extend-0.6.0.tgz", - "integrity": "sha512-LOHxIOaPYdHlJRtCQfDIVZtfw/ufM8+rVj649RIHzcm/vGwQRXFt6OPqIFWsm2XEMrNIEtWR64sY1LEKD2vAOA==", - "engines": { - "node": ">=4.0.0" - } - }, "node_modules/deep-is": { "version": "0.1.4", "resolved": "https://registry.npmjs.org/deep-is/-/deep-is-0.1.4.tgz", @@ -15433,14 +15366,6 @@ "url": "https://github.com/sponsors/wooorm" } }, - "node_modules/detect-libc": { - "version": "2.0.1", - "resolved": "https://registry.npmjs.org/detect-libc/-/detect-libc-2.0.1.tgz", - "integrity": "sha512-463v3ZeIrcWtdgIg6vI6XUncguvr2TnGl4SzDXinkt9mSLpBJKXT3mW6xT3VQdDN11+WVs29pgvivTc4Lp8v+w==", - "engines": { - "node": ">=8" - } - }, "node_modules/detect-node-es": { "version": "1.1.0", "resolved": "https://registry.npmjs.org/detect-node-es/-/detect-node-es-1.1.0.tgz", @@ -15803,6 +15728,7 @@ "version": "1.4.4", "resolved": "https://registry.npmjs.org/end-of-stream/-/end-of-stream-1.4.4.tgz", "integrity": "sha512-+uw1inIHVPQoaVuHzRyXd21icM+cnt4CzD5rW+NC1wjOUSTOs+Te7FOv7AhN7vS9x/oIyhLP5PR1H+phQAHu5Q==", + "dev": true, "dependencies": { "once": "^1.4.0" } @@ -16925,14 +16851,6 @@ "integrity": "sha512-Tpp60P6IUJDTuOq/5Z8cdskzJujfwqfOTkrwIwj7IRISpnkJnT6SyJ4PCPnGMoFjC9ddhal5KVIYtAt97ix05A==", "dev": true }, - "node_modules/expand-template": { - "version": "2.0.3", - "resolved": "https://registry.npmjs.org/expand-template/-/expand-template-2.0.3.tgz", - "integrity": "sha512-XYfuKMvj4O35f/pOXLObndIRvyQ+/+6AhODh+OKWj9S9498pHHn/IMszH+gt0fBCRWMNfk1ZSp5x3AifmnI2vg==", - "engines": { - "node": ">=6" - } - }, "node_modules/express": { "version": "4.18.2", "resolved": "https://registry.npmjs.org/express/-/express-4.18.2.tgz", @@ -17908,11 +17826,6 @@ "safe-buffer": "~5.1.0" } }, - "node_modules/fs-constants": { - "version": "1.0.0", - "resolved": "https://registry.npmjs.org/fs-constants/-/fs-constants-1.0.0.tgz", - "integrity": "sha512-y6OAwoSIf7FyjMIv94u+b5rdheZEjzR63GTyZJm5qh4Bi+2YgwLCcI/fPFZkL5PSixOt6ZNKm+w+Hfp/Bciwow==" - }, "node_modules/fs-extra": { "version": "9.1.0", "resolved": "https://registry.npmjs.org/fs-extra/-/fs-extra-9.1.0.tgz", @@ -18178,11 +18091,6 @@ "assert-plus": "^1.0.0" } }, - "node_modules/github-from-package": { - "version": "0.0.0", - "resolved": "https://registry.npmjs.org/github-from-package/-/github-from-package-0.0.0.tgz", - "integrity": "sha512-SyHy3T1v2NUXn29OsWdxmK6RwHD+vkj3v8en8AOBZ1wBQ/hCAQ5bAQTD02kW4W9tUp/3Qh6J8r9EvntiyCmOOw==" - }, "node_modules/github-slugger": { "version": "1.5.0", "resolved": "https://registry.npmjs.org/github-slugger/-/github-slugger-1.5.0.tgz", @@ -18933,6 +18841,7 @@ "version": "1.2.1", "resolved": "https://registry.npmjs.org/ieee754/-/ieee754-1.2.1.tgz", "integrity": "sha512-dcyqhDvX1C46lXZcVqCpK+FtMRQVdIMN6/Df5js2zouUsqG7I6sFxitIC+7KYK29KdXOLHdu9zL4sFnoVQnqaA==", + "dev": true, "funding": [ { "type": "github", @@ -21216,17 +21125,6 @@ "node": ">=6" } }, - "node_modules/mimic-response": { - "version": "3.1.0", - "resolved": "https://registry.npmjs.org/mimic-response/-/mimic-response-3.1.0.tgz", - "integrity": "sha512-z0yWI+4FDrrweS8Zmt4Ej5HdJmky15+L2e6Wgn3+iK5fWzb6T3fhNFq2+MeTRb064c6Wr4N/wv0DzQTjNzHNGQ==", - "engines": { - "node": ">=10" - }, - "funding": { - "url": "https://github.com/sponsors/sindresorhus" - } - }, "node_modules/min-document": { "version": "2.19.0", "resolved": "https://registry.npmjs.org/min-document/-/min-document-2.19.0.tgz", @@ -21403,11 +21301,6 @@ "node": ">=10" } }, - "node_modules/mkdirp-classic": { - "version": "0.5.3", - "resolved": "https://registry.npmjs.org/mkdirp-classic/-/mkdirp-classic-0.5.3.tgz", - "integrity": "sha512-gKLcREMhtuZRwRAfqP3RFW+TK4JqApVBtOIftVgjuABpAtpxhPGaDcfvbhNvD0B8iD1oUr/txX35NjcaY6Ns/A==" - }, "node_modules/move-concurrently": { "version": "1.0.1", "resolved": "https://registry.npmjs.org/move-concurrently/-/move-concurrently-1.0.1.tgz", @@ -21497,11 +21390,6 @@ "node": ">=0.10.0" } }, - "node_modules/napi-build-utils": { - "version": "1.0.2", - "resolved": "https://registry.npmjs.org/napi-build-utils/-/napi-build-utils-1.0.2.tgz", - "integrity": "sha512-ONmRUqK7zj7DWX0D9ADe03wbwOBZxNAfF20PlGfCWQcD3+/MakShIHrMqx9YwPTfxDdF1zLeL+RGZiR9kGMLdg==" - }, "node_modules/natural-compare": { "version": "1.4.0", "resolved": "https://registry.npmjs.org/natural-compare/-/natural-compare-1.4.0.tgz", @@ -21654,52 +21542,6 @@ "tslib": "^2.0.3" } }, - "node_modules/node-abi": { - "version": "3.30.0", - "resolved": "https://registry.npmjs.org/node-abi/-/node-abi-3.30.0.tgz", - "integrity": "sha512-qWO5l3SCqbwQavymOmtTVuCWZE23++S+rxyoHjXqUmPyzRcaoI4lA2gO55/drddGnedAyjA7sk76SfQ5lfUMnw==", - "dependencies": { - "semver": "^7.3.5" - }, - "engines": { - "node": ">=10" - } - }, - "node_modules/node-abi/node_modules/lru-cache": { - "version": "6.0.0", - "resolved": "https://registry.npmjs.org/lru-cache/-/lru-cache-6.0.0.tgz", - "integrity": "sha512-Jo6dJ04CmSjuznwJSS3pUeWmd/H0ffTlkXXgwZi+eq1UCmqQwCh+eLsYOYCwY991i2Fah4h1BEMCx4qThGbsiA==", - "dependencies": { - "yallist": "^4.0.0" - }, - "engines": { - "node": ">=10" - } - }, - "node_modules/node-abi/node_modules/semver": { - "version": "7.3.8", - "resolved": "https://registry.npmjs.org/semver/-/semver-7.3.8.tgz", - "integrity": "sha512-NB1ctGL5rlHrPJtFDVIVzTyQylMLu9N9VICA6HSFJo8MCGVTMW6gfpicwKmmK/dAjTOrqu5l63JJOpDSrAis3A==", - "dependencies": { - "lru-cache": "^6.0.0" - }, - "bin": { - "semver": "bin/semver.js" - }, - "engines": { - "node": ">=10" - } - }, - "node_modules/node-abi/node_modules/yallist": { - "version": "4.0.0", - "resolved": "https://registry.npmjs.org/yallist/-/yallist-4.0.0.tgz", - "integrity": "sha512-3wdGidZyq5PB084XLES5TpOSRA3wjXAlIWMhum2kRcv/41Sn2emQ0dycQW4uZXLejwKvg6EsvbdlVL+FYEct7A==" - }, - "node_modules/node-addon-api": { - "version": "5.0.0", - "resolved": "https://registry.npmjs.org/node-addon-api/-/node-addon-api-5.0.0.tgz", - "integrity": "sha512-CvkDw2OEnme7ybCykJpVcKH+uAOLV2qLqiyla128dN9TkEWfrYmxG6C2boDe5KcNQqZF3orkqzGgOMvZ/JNekA==" - }, "node_modules/node-dir": { "version": "0.1.17", "resolved": "https://registry.npmjs.org/node-dir/-/node-dir-0.1.17.tgz", @@ -25958,31 +25800,6 @@ "resolved": "https://registry.npmjs.org/pretty-format/-/pretty-format-3.8.0.tgz", "integrity": "sha512-WuxUnVtlWL1OfZFQFuqvnvs6MiAGk9UNsBostyBOB0Is9wb5uRESevA6rnl/rkksXaGX3GzZhPup5d6Vp1nFew==" }, - "node_modules/prebuild-install": { - "version": "7.1.1", - "resolved": "https://registry.npmjs.org/prebuild-install/-/prebuild-install-7.1.1.tgz", - "integrity": "sha512-jAXscXWMcCK8GgCoHOfIr0ODh5ai8mj63L2nWrjuAgXE6tDyYGnx4/8o/rCgU+B4JSyZBKbeZqzhtwtC3ovxjw==", - "dependencies": { - "detect-libc": "^2.0.0", - "expand-template": "^2.0.3", - "github-from-package": "0.0.0", - "minimist": "^1.2.3", - "mkdirp-classic": "^0.5.3", - "napi-build-utils": "^1.0.1", - "node-abi": "^3.3.0", - "pump": "^3.0.0", - "rc": "^1.2.7", - "simple-get": "^4.0.0", - "tar-fs": "^2.0.0", - "tunnel-agent": "^0.6.0" - }, - "bin": { - "prebuild-install": "bin.js" - }, - "engines": { - "node": ">=10" - } - }, "node_modules/prelude-ls": { "version": "1.2.1", "resolved": "https://registry.npmjs.org/prelude-ls/-/prelude-ls-1.2.1.tgz", @@ -26234,6 +26051,7 @@ "version": "3.0.0", "resolved": "https://registry.npmjs.org/pump/-/pump-3.0.0.tgz", "integrity": "sha512-LwZy+p3SFs1Pytd/jYct4wpv49HiYCqd9Rlc5ZVdk0V+8Yzv6jR5Blk3TRmPL1ft69TxP0IMZGJ+WPFU2BFhww==", + "dev": true, "dependencies": { "end-of-stream": "^1.1.0", "once": "^1.3.1" @@ -26414,33 +26232,6 @@ "webpack": "^4.0.0 || ^5.0.0" } }, - "node_modules/rc": { - "version": "1.2.8", - "resolved": "https://registry.npmjs.org/rc/-/rc-1.2.8.tgz", - "integrity": "sha512-y3bGgqKj3QBdxLbLkomlohkvsA8gdAiUQlSBJnBhfn+BPxg4bc62d8TcBW15wavDfgexCgccckhcZvywyQYPOw==", - "dependencies": { - "deep-extend": "^0.6.0", - "ini": "~1.3.0", - "minimist": "^1.2.0", - "strip-json-comments": "~2.0.1" - }, - "bin": { - "rc": "cli.js" - } - }, - "node_modules/rc/node_modules/ini": { - "version": "1.3.8", - "resolved": "https://registry.npmjs.org/ini/-/ini-1.3.8.tgz", - "integrity": "sha512-JV/yugV2uzW5iMRSiZAyDtQd+nxtUnjeLt0acNdw98kKLrvuRVyB80tsREOE7yvGVgalhZ6RNXCmEHkUKBKxew==" - }, - "node_modules/rc/node_modules/strip-json-comments": { - "version": "2.0.1", - "resolved": "https://registry.npmjs.org/strip-json-comments/-/strip-json-comments-2.0.1.tgz", - "integrity": "sha512-4gB8na07fecVVkOI6Rs4e7T6NOTki5EmL7TUduTs6bu3EdnSycntVJ4re8kgZA+wx9IueI2Y11bfbgwtzuE0KQ==", - "engines": { - "node": ">=0.10.0" - } - }, "node_modules/react": { "version": "18.2.0", "resolved": "https://registry.npmjs.org/react/-/react-18.2.0.tgz", @@ -26765,6 +26556,7 @@ "version": "3.6.0", "resolved": "https://registry.npmjs.org/readable-stream/-/readable-stream-3.6.0.tgz", "integrity": "sha512-BViHy7LKeTz4oNnkcLJ+lVSL6vpiFeX6/d3oSH8zCW7UxP2onchk+vTGB143xuFjHS3deTgkKoXXymXqymiIdA==", + "dev": true, "dependencies": { "inherits": "^2.0.3", "string_decoder": "^1.1.1", @@ -27366,7 +27158,8 @@ "node_modules/safe-buffer": { "version": "5.1.2", "resolved": "https://registry.npmjs.org/safe-buffer/-/safe-buffer-5.1.2.tgz", - "integrity": "sha512-Gd2UZBJDkXlY7GbJxfsE8/nvKkUEU1G38c1siN6QP6a9PT9MmHB8GnpscSmMJSoF8LOIrt8ud/wPtojys4G6+g==" + "integrity": "sha512-Gd2UZBJDkXlY7GbJxfsE8/nvKkUEU1G38c1siN6QP6a9PT9MmHB8GnpscSmMJSoF8LOIrt8ud/wPtojys4G6+g==", + "dev": true }, "node_modules/safe-regex": { "version": "1.1.0", @@ -27906,58 +27699,6 @@ "node": ">=8" } }, - "node_modules/sharp": { - "version": "0.31.2", - "resolved": "https://registry.npmjs.org/sharp/-/sharp-0.31.2.tgz", - "integrity": "sha512-DUdNVEXgS5A97cTagSLIIp8dUZ/lZtk78iNVZgHdHbx1qnQR7JAHY0BnXnwwH39Iw+VKhO08CTYhIg0p98vQ5Q==", - "hasInstallScript": true, - "dependencies": { - "color": "^4.2.3", - "detect-libc": "^2.0.1", - "node-addon-api": "^5.0.0", - "prebuild-install": "^7.1.1", - "semver": "^7.3.8", - "simple-get": "^4.0.1", - "tar-fs": "^2.1.1", - "tunnel-agent": "^0.6.0" - }, - "engines": { - "node": ">=14.15.0" - }, - "funding": { - "url": "https://opencollective.com/libvips" - } - }, - "node_modules/sharp/node_modules/lru-cache": { - "version": "6.0.0", - "resolved": "https://registry.npmjs.org/lru-cache/-/lru-cache-6.0.0.tgz", - "integrity": "sha512-Jo6dJ04CmSjuznwJSS3pUeWmd/H0ffTlkXXgwZi+eq1UCmqQwCh+eLsYOYCwY991i2Fah4h1BEMCx4qThGbsiA==", - "dependencies": { - "yallist": "^4.0.0" - }, - "engines": { - "node": ">=10" - } - }, - "node_modules/sharp/node_modules/semver": { - "version": "7.3.8", - "resolved": "https://registry.npmjs.org/semver/-/semver-7.3.8.tgz", - "integrity": "sha512-NB1ctGL5rlHrPJtFDVIVzTyQylMLu9N9VICA6HSFJo8MCGVTMW6gfpicwKmmK/dAjTOrqu5l63JJOpDSrAis3A==", - "dependencies": { - "lru-cache": "^6.0.0" - }, - "bin": { - "semver": "bin/semver.js" - }, - "engines": { - "node": ">=10" - } - }, - "node_modules/sharp/node_modules/yallist": { - "version": "4.0.0", - "resolved": "https://registry.npmjs.org/yallist/-/yallist-4.0.0.tgz", - "integrity": "sha512-3wdGidZyq5PB084XLES5TpOSRA3wjXAlIWMhum2kRcv/41Sn2emQ0dycQW4uZXLejwKvg6EsvbdlVL+FYEct7A==" - }, "node_modules/shebang-command": { "version": "2.0.0", "resolved": "https://registry.npmjs.org/shebang-command/-/shebang-command-2.0.0.tgz", @@ -27996,62 +27737,6 @@ "integrity": "sha512-wnD2ZE+l+SPC/uoS0vXeE9L1+0wuaMqKlfz9AMUo38JsyLSBWSFcHR1Rri62LZc12vLr1gb3jl7iwQhgwpAbGQ==", "dev": true }, - "node_modules/simple-concat": { - "version": "1.0.1", - "resolved": "https://registry.npmjs.org/simple-concat/-/simple-concat-1.0.1.tgz", - "integrity": "sha512-cSFtAPtRhljv69IK0hTVZQ+OfE9nePi/rtJmw5UjHeVyVroEqJXP1sFztKUy1qU+xvz3u/sfYJLa947b7nAN2Q==", - "funding": [ - { - "type": "github", - "url": "https://github.com/sponsors/feross" - }, - { - "type": "patreon", - "url": "https://www.patreon.com/feross" - }, - { - "type": "consulting", - "url": "https://feross.org/support" - } - ] - }, - "node_modules/simple-get": { - "version": "4.0.1", - "resolved": "https://registry.npmjs.org/simple-get/-/simple-get-4.0.1.tgz", - "integrity": "sha512-brv7p5WgH0jmQJr1ZDDfKDOSeWWg+OVypG99A/5vYGPqJ6pxiaHLy8nxtFjBA7oMa01ebA9gfh1uMCFqOuXxvA==", - "funding": [ - { - "type": "github", - "url": "https://github.com/sponsors/feross" - }, - { - "type": "patreon", - "url": "https://www.patreon.com/feross" - }, - { - "type": "consulting", - "url": "https://feross.org/support" - } - ], - "dependencies": { - "decompress-response": "^6.0.0", - "once": "^1.3.1", - "simple-concat": "^1.0.0" - } - }, - "node_modules/simple-swizzle": { - "version": "0.2.2", - "resolved": "https://registry.npmjs.org/simple-swizzle/-/simple-swizzle-0.2.2.tgz", - "integrity": "sha512-JA//kQgZtbuY83m+xT+tXJkmJncGMTFT+C+g2h2R9uxkYIrE2yy9sgmcLhCnw57/WSD+Eh3J97FPEDFnbXnDUg==", - "dependencies": { - "is-arrayish": "^0.3.1" - } - }, - "node_modules/simple-swizzle/node_modules/is-arrayish": { - "version": "0.3.2", - "resolved": "https://registry.npmjs.org/is-arrayish/-/is-arrayish-0.3.2.tgz", - "integrity": "sha512-eVRqCvVlZbuw3GrM63ovNSNAeA1K16kaR/LRY/92w0zxQ5/1YzwblUX652i4Xs9RwAGjW9d9y6X88t8OaAJfWQ==" - }, "node_modules/sisteransi": { "version": "1.0.5", "resolved": "https://registry.npmjs.org/sisteransi/-/sisteransi-1.0.5.tgz", @@ -28715,6 +28400,7 @@ "version": "1.3.0", "resolved": "https://registry.npmjs.org/string_decoder/-/string_decoder-1.3.0.tgz", "integrity": "sha512-hkRX8U1WjJFd8LsDJ2yQ/wWWxaopEsABU1XfkM8A+j0+85JAGppt16cr1Whg6KIbb4okU6Mql6BOj+uup/wKeA==", + "dev": true, "dependencies": { "safe-buffer": "~5.2.0" } @@ -28723,6 +28409,7 @@ "version": "5.2.1", "resolved": "https://registry.npmjs.org/safe-buffer/-/safe-buffer-5.2.1.tgz", "integrity": "sha512-rp3So07KcdmmKbGvgaNxQSJr7bGVSVk5S9Eq1F+ppbRo70+YeaDxkw5Dd8NPN+GD6bjnYm2VuPuCXmpuYvmCXQ==", + "dev": true, "funding": [ { "type": "github", @@ -29137,32 +28824,6 @@ "node": ">=10" } }, - "node_modules/tar-fs": { - "version": "2.1.1", - "resolved": "https://registry.npmjs.org/tar-fs/-/tar-fs-2.1.1.tgz", - "integrity": "sha512-V0r2Y9scmbDRLCNex/+hYzvp/zyYjvFbHPNgVTKfQvVrb6guiE/fxP+XblDNR011utopbkex2nM4dHNV6GDsng==", - "dependencies": { - "chownr": "^1.1.1", - "mkdirp-classic": "^0.5.2", - "pump": "^3.0.0", - "tar-stream": "^2.1.4" - } - }, - "node_modules/tar-stream": { - "version": "2.2.0", - "resolved": "https://registry.npmjs.org/tar-stream/-/tar-stream-2.2.0.tgz", - "integrity": "sha512-ujeqbceABgwMZxEJnk2HDY2DlnUZ+9oEcb1KzTVfYHio0UE6dG71n60d8D2I4qNvleWrrXpmjpt7vZeF1LnMZQ==", - "dependencies": { - "bl": "^4.0.3", - "end-of-stream": "^1.4.1", - "fs-constants": "^1.0.0", - "inherits": "^2.0.3", - "readable-stream": "^3.1.1" - }, - "engines": { - "node": ">=6" - } - }, "node_modules/tar/node_modules/chownr": { "version": "2.0.0", "resolved": "https://registry.npmjs.org/chownr/-/chownr-2.0.0.tgz", @@ -29656,6 +29317,7 @@ "version": "0.6.0", "resolved": "https://registry.npmjs.org/tunnel-agent/-/tunnel-agent-0.6.0.tgz", "integrity": "sha512-McnNiV1l8RYeY8tBgEpuodCC1mLUdbSN+CYBL7kJsJNInOP8UjDDEwdk6Mw60vdLLrr5NHKZhMAOSrR2NZuQ+w==", + "dev": true, "dependencies": { "safe-buffer": "^5.0.1" }, @@ -40790,7 +40452,8 @@ "base64-js": { "version": "1.5.1", "resolved": "https://registry.npmjs.org/base64-js/-/base64-js-1.5.1.tgz", - "integrity": "sha512-AKpaYlHn8t4SVbOHCy+b5+KKgvR4vrsD8vbvrbiQJps7fKDTkjkDry6ji0rUJjC0kzbNePLwzxq8iypo41qeWA==" + "integrity": "sha512-AKpaYlHn8t4SVbOHCy+b5+KKgvR4vrsD8vbvrbiQJps7fKDTkjkDry6ji0rUJjC0kzbNePLwzxq8iypo41qeWA==", + "dev": true }, "bcrypt-pbkdf": { "version": "1.0.2", @@ -40850,16 +40513,6 @@ "file-uri-to-path": "1.0.0" } }, - "bl": { - "version": "4.1.0", - "resolved": "https://registry.npmjs.org/bl/-/bl-4.1.0.tgz", - "integrity": "sha512-1W07cM9gS6DcLperZfFSj+bWLtaPGSOHWhPiGzXmvVJbRLdG82sH/Kn8EtW1VqWVA54AKf2h5k5BbnIbwF3h6w==", - "requires": { - "buffer": "^5.5.0", - "inherits": "^2.0.4", - "readable-stream": "^3.4.0" - } - }, "blob-util": { "version": "2.0.2", "resolved": "https://registry.npmjs.org/blob-util/-/blob-util-2.0.2.tgz", @@ -41149,6 +40802,7 @@ "version": "5.7.1", "resolved": "https://registry.npmjs.org/buffer/-/buffer-5.7.1.tgz", "integrity": "sha512-EHcyIPBQ4BSGlvjB16k5KgAJ27CIsHY/2JBmCRReo48y9rQ3MaUzWX3KVlBa4U7MyX02HdVj0K7C3WaB3ju7FQ==", + "dev": true, "requires": { "base64-js": "^1.3.1", "ieee754": "^1.1.13" @@ -41447,7 +41101,8 @@ "chownr": { "version": "1.1.4", "resolved": "https://registry.npmjs.org/chownr/-/chownr-1.1.4.tgz", - "integrity": "sha512-jJ0bqzaylmJtVnNgzTeSOs8DPavpbYgEr/b0YL8/2GO3xJEhInFmhKMUnEJQjZumK7KXGFhUy89PrsJWlakBVg==" + "integrity": "sha512-jJ0bqzaylmJtVnNgzTeSOs8DPavpbYgEr/b0YL8/2GO3xJEhInFmhKMUnEJQjZumK7KXGFhUy89PrsJWlakBVg==", + "dev": true }, "chrome-trace-event": { "version": "1.0.3", @@ -41663,30 +41318,6 @@ "object-visit": "^1.0.0" } }, - "color": { - "version": "4.2.3", - "resolved": "https://registry.npmjs.org/color/-/color-4.2.3.tgz", - "integrity": "sha512-1rXeuUUiGGrykh+CeBdu5Ie7OJwinCgQY0bc7GCRxy5xVHy+moaqkpL/jqQq0MtQOeYcrqEz4abc5f0KtU7W4A==", - "requires": { - "color-convert": "^2.0.1", - "color-string": "^1.9.0" - }, - "dependencies": { - "color-convert": { - "version": "2.0.1", - "resolved": "https://registry.npmjs.org/color-convert/-/color-convert-2.0.1.tgz", - "integrity": "sha512-RRECPsj7iu/xb5oKYcsFHSppFNnsj/52OVTRKb4zP5onXwVF3zVmmToNcOfGC+CRDpfK/U584fMg38ZHCaElKQ==", - "requires": { - "color-name": "~1.1.4" - } - }, - "color-name": { - "version": "1.1.4", - "resolved": "https://registry.npmjs.org/color-name/-/color-name-1.1.4.tgz", - "integrity": "sha512-dOy+3AuW3a2wNbZHIuMZpTcgjGuLU/uBL/ubcZF9OXbDo8ff4O8yVp5Bf0efS8uEoYo5q4Fx7dY9OgQGXgAsQA==" - } - } - }, "color-convert": { "version": "1.9.3", "resolved": "https://registry.npmjs.org/color-convert/-/color-convert-1.9.3.tgz", @@ -41700,15 +41331,6 @@ "resolved": "https://registry.npmjs.org/color-name/-/color-name-1.1.3.tgz", "integrity": "sha512-72fSenhMw2HZMTVHeCA9KCmpEIbzWiQsjN+BHcBbS9vr1mtt+vJjPdksIBNUmKAW8TFUDPJK5SUU3QhE9NEXDw==" }, - "color-string": { - "version": "1.9.1", - "resolved": "https://registry.npmjs.org/color-string/-/color-string-1.9.1.tgz", - "integrity": "sha512-shrVawQFojnZv6xM40anx4CkoDP+fZsw/ZerEMsW/pyzsRbElpsL/DBVW7q3ExxwusdNXI3lXpuhEZkzs8p5Eg==", - "requires": { - "color-name": "^1.0.0", - "simple-swizzle": "^0.2.2" - } - }, "color-support": { "version": "1.1.3", "resolved": "https://registry.npmjs.org/color-support/-/color-support-1.1.3.tgz", @@ -42720,14 +42342,6 @@ "integrity": "sha512-FqUYQ+8o158GyGTrMFJms9qh3CqTKvAqgqsTnkLI8sKu0028orqBhxNMFkFen0zGyg6epACD32pjVk58ngIErQ==", "dev": true }, - "decompress-response": { - "version": "6.0.0", - "resolved": "https://registry.npmjs.org/decompress-response/-/decompress-response-6.0.0.tgz", - "integrity": "sha512-aW35yZM6Bb/4oJlZncMH2LCoZtJXTRxES17vE3hoRiowU2kWHaJKFkSBDnDR+cm9J+9QhXmREyIfv0pji9ejCQ==", - "requires": { - "mimic-response": "^3.1.0" - } - }, "dedent": { "version": "0.7.0", "resolved": "https://registry.npmjs.org/dedent/-/dedent-0.7.0.tgz", @@ -42757,11 +42371,6 @@ "which-typed-array": "^1.1.8" } }, - "deep-extend": { - "version": "0.6.0", - "resolved": "https://registry.npmjs.org/deep-extend/-/deep-extend-0.6.0.tgz", - "integrity": "sha512-LOHxIOaPYdHlJRtCQfDIVZtfw/ufM8+rVj649RIHzcm/vGwQRXFt6OPqIFWsm2XEMrNIEtWR64sY1LEKD2vAOA==" - }, "deep-is": { "version": "0.1.4", "resolved": "https://registry.npmjs.org/deep-is/-/deep-is-0.1.4.tgz", @@ -42868,11 +42477,6 @@ "repeat-string": "^1.5.4" } }, - "detect-libc": { - "version": "2.0.1", - "resolved": "https://registry.npmjs.org/detect-libc/-/detect-libc-2.0.1.tgz", - "integrity": "sha512-463v3ZeIrcWtdgIg6vI6XUncguvr2TnGl4SzDXinkt9mSLpBJKXT3mW6xT3VQdDN11+WVs29pgvivTc4Lp8v+w==" - }, "detect-node-es": { "version": "1.1.0", "resolved": "https://registry.npmjs.org/detect-node-es/-/detect-node-es-1.1.0.tgz", @@ -43178,6 +42782,7 @@ "version": "1.4.4", "resolved": "https://registry.npmjs.org/end-of-stream/-/end-of-stream-1.4.4.tgz", "integrity": "sha512-+uw1inIHVPQoaVuHzRyXd21icM+cnt4CzD5rW+NC1wjOUSTOs+Te7FOv7AhN7vS9x/oIyhLP5PR1H+phQAHu5Q==", + "dev": true, "requires": { "once": "^1.4.0" } @@ -44034,11 +43639,6 @@ } } }, - "expand-template": { - "version": "2.0.3", - "resolved": "https://registry.npmjs.org/expand-template/-/expand-template-2.0.3.tgz", - "integrity": "sha512-XYfuKMvj4O35f/pOXLObndIRvyQ+/+6AhODh+OKWj9S9498pHHn/IMszH+gt0fBCRWMNfk1ZSp5x3AifmnI2vg==" - }, "express": { "version": "4.18.2", "resolved": "https://registry.npmjs.org/express/-/express-4.18.2.tgz", @@ -44815,11 +44415,6 @@ } } }, - "fs-constants": { - "version": "1.0.0", - "resolved": "https://registry.npmjs.org/fs-constants/-/fs-constants-1.0.0.tgz", - "integrity": "sha512-y6OAwoSIf7FyjMIv94u+b5rdheZEjzR63GTyZJm5qh4Bi+2YgwLCcI/fPFZkL5PSixOt6ZNKm+w+Hfp/Bciwow==" - }, "fs-extra": { "version": "9.1.0", "resolved": "https://registry.npmjs.org/fs-extra/-/fs-extra-9.1.0.tgz", @@ -45026,11 +44621,6 @@ "assert-plus": "^1.0.0" } }, - "github-from-package": { - "version": "0.0.0", - "resolved": "https://registry.npmjs.org/github-from-package/-/github-from-package-0.0.0.tgz", - "integrity": "sha512-SyHy3T1v2NUXn29OsWdxmK6RwHD+vkj3v8en8AOBZ1wBQ/hCAQ5bAQTD02kW4W9tUp/3Qh6J8r9EvntiyCmOOw==" - }, "github-slugger": { "version": "1.5.0", "resolved": "https://registry.npmjs.org/github-slugger/-/github-slugger-1.5.0.tgz", @@ -45594,7 +45184,8 @@ "ieee754": { "version": "1.2.1", "resolved": "https://registry.npmjs.org/ieee754/-/ieee754-1.2.1.tgz", - "integrity": "sha512-dcyqhDvX1C46lXZcVqCpK+FtMRQVdIMN6/Df5js2zouUsqG7I6sFxitIC+7KYK29KdXOLHdu9zL4sFnoVQnqaA==" + "integrity": "sha512-dcyqhDvX1C46lXZcVqCpK+FtMRQVdIMN6/Df5js2zouUsqG7I6sFxitIC+7KYK29KdXOLHdu9zL4sFnoVQnqaA==", + "dev": true }, "iferr": { "version": "0.1.5", @@ -47285,11 +46876,6 @@ "integrity": "sha512-OqbOk5oEQeAZ8WXWydlu9HJjz9WVdEIvamMCcXmuqUYjTknH/sqsWvhQ3vgwKFRR1HpjvNBKQ37nbJgYzGqGcg==", "dev": true }, - "mimic-response": { - "version": "3.1.0", - "resolved": "https://registry.npmjs.org/mimic-response/-/mimic-response-3.1.0.tgz", - "integrity": "sha512-z0yWI+4FDrrweS8Zmt4Ej5HdJmky15+L2e6Wgn3+iK5fWzb6T3fhNFq2+MeTRb064c6Wr4N/wv0DzQTjNzHNGQ==" - }, "min-document": { "version": "2.19.0", "resolved": "https://registry.npmjs.org/min-document/-/min-document-2.19.0.tgz", @@ -47431,11 +47017,6 @@ "integrity": "sha512-vVqVZQyf3WLx2Shd0qJ9xuvqgAyKPLAiqITEtqW0oIUjzo3PePDd6fW9iFz30ef7Ysp/oiWqbhszeGWW2T6Gzw==", "dev": true }, - "mkdirp-classic": { - "version": "0.5.3", - "resolved": "https://registry.npmjs.org/mkdirp-classic/-/mkdirp-classic-0.5.3.tgz", - "integrity": "sha512-gKLcREMhtuZRwRAfqP3RFW+TK4JqApVBtOIftVgjuABpAtpxhPGaDcfvbhNvD0B8iD1oUr/txX35NjcaY6Ns/A==" - }, "move-concurrently": { "version": "1.0.1", "resolved": "https://registry.npmjs.org/move-concurrently/-/move-concurrently-1.0.1.tgz", @@ -47512,11 +47093,6 @@ "to-regex": "^3.0.1" } }, - "napi-build-utils": { - "version": "1.0.2", - "resolved": "https://registry.npmjs.org/napi-build-utils/-/napi-build-utils-1.0.2.tgz", - "integrity": "sha512-ONmRUqK7zj7DWX0D9ADe03wbwOBZxNAfF20PlGfCWQcD3+/MakShIHrMqx9YwPTfxDdF1zLeL+RGZiR9kGMLdg==" - }, "natural-compare": { "version": "1.4.0", "resolved": "https://registry.npmjs.org/natural-compare/-/natural-compare-1.4.0.tgz", @@ -47615,42 +47191,6 @@ "tslib": "^2.0.3" } }, - "node-abi": { - "version": "3.30.0", - "resolved": "https://registry.npmjs.org/node-abi/-/node-abi-3.30.0.tgz", - "integrity": "sha512-qWO5l3SCqbwQavymOmtTVuCWZE23++S+rxyoHjXqUmPyzRcaoI4lA2gO55/drddGnedAyjA7sk76SfQ5lfUMnw==", - "requires": { - "semver": "^7.3.5" - }, - "dependencies": { - "lru-cache": { - "version": "6.0.0", - "resolved": "https://registry.npmjs.org/lru-cache/-/lru-cache-6.0.0.tgz", - "integrity": "sha512-Jo6dJ04CmSjuznwJSS3pUeWmd/H0ffTlkXXgwZi+eq1UCmqQwCh+eLsYOYCwY991i2Fah4h1BEMCx4qThGbsiA==", - "requires": { - "yallist": "^4.0.0" - } - }, - "semver": { - "version": "7.3.8", - "resolved": "https://registry.npmjs.org/semver/-/semver-7.3.8.tgz", - "integrity": "sha512-NB1ctGL5rlHrPJtFDVIVzTyQylMLu9N9VICA6HSFJo8MCGVTMW6gfpicwKmmK/dAjTOrqu5l63JJOpDSrAis3A==", - "requires": { - "lru-cache": "^6.0.0" - } - }, - "yallist": { - "version": "4.0.0", - "resolved": "https://registry.npmjs.org/yallist/-/yallist-4.0.0.tgz", - "integrity": "sha512-3wdGidZyq5PB084XLES5TpOSRA3wjXAlIWMhum2kRcv/41Sn2emQ0dycQW4uZXLejwKvg6EsvbdlVL+FYEct7A==" - } - } - }, - "node-addon-api": { - "version": "5.0.0", - "resolved": "https://registry.npmjs.org/node-addon-api/-/node-addon-api-5.0.0.tgz", - "integrity": "sha512-CvkDw2OEnme7ybCykJpVcKH+uAOLV2qLqiyla128dN9TkEWfrYmxG6C2boDe5KcNQqZF3orkqzGgOMvZ/JNekA==" - }, "node-dir": { "version": "0.1.17", "resolved": "https://registry.npmjs.org/node-dir/-/node-dir-0.1.17.tgz", @@ -50621,25 +50161,6 @@ } } }, - "prebuild-install": { - "version": "7.1.1", - "resolved": "https://registry.npmjs.org/prebuild-install/-/prebuild-install-7.1.1.tgz", - "integrity": "sha512-jAXscXWMcCK8GgCoHOfIr0ODh5ai8mj63L2nWrjuAgXE6tDyYGnx4/8o/rCgU+B4JSyZBKbeZqzhtwtC3ovxjw==", - "requires": { - "detect-libc": "^2.0.0", - "expand-template": "^2.0.3", - "github-from-package": "0.0.0", - "minimist": "^1.2.3", - "mkdirp-classic": "^0.5.3", - "napi-build-utils": "^1.0.1", - "node-abi": "^3.3.0", - "pump": "^3.0.0", - "rc": "^1.2.7", - "simple-get": "^4.0.0", - "tar-fs": "^2.0.0", - "tunnel-agent": "^0.6.0" - } - }, "prelude-ls": { "version": "1.2.1", "resolved": "https://registry.npmjs.org/prelude-ls/-/prelude-ls-1.2.1.tgz", @@ -50832,6 +50353,7 @@ "version": "3.0.0", "resolved": "https://registry.npmjs.org/pump/-/pump-3.0.0.tgz", "integrity": "sha512-LwZy+p3SFs1Pytd/jYct4wpv49HiYCqd9Rlc5ZVdk0V+8Yzv6jR5Blk3TRmPL1ft69TxP0IMZGJ+WPFU2BFhww==", + "dev": true, "requires": { "end-of-stream": "^1.1.0", "once": "^1.3.1" @@ -50957,29 +50479,6 @@ "schema-utils": "^3.0.0" } }, - "rc": { - "version": "1.2.8", - "resolved": "https://registry.npmjs.org/rc/-/rc-1.2.8.tgz", - "integrity": "sha512-y3bGgqKj3QBdxLbLkomlohkvsA8gdAiUQlSBJnBhfn+BPxg4bc62d8TcBW15wavDfgexCgccckhcZvywyQYPOw==", - "requires": { - "deep-extend": "^0.6.0", - "ini": "~1.3.0", - "minimist": "^1.2.0", - "strip-json-comments": "~2.0.1" - }, - "dependencies": { - "ini": { - "version": "1.3.8", - "resolved": "https://registry.npmjs.org/ini/-/ini-1.3.8.tgz", - "integrity": "sha512-JV/yugV2uzW5iMRSiZAyDtQd+nxtUnjeLt0acNdw98kKLrvuRVyB80tsREOE7yvGVgalhZ6RNXCmEHkUKBKxew==" - }, - "strip-json-comments": { - "version": "2.0.1", - "resolved": "https://registry.npmjs.org/strip-json-comments/-/strip-json-comments-2.0.1.tgz", - "integrity": "sha512-4gB8na07fecVVkOI6Rs4e7T6NOTki5EmL7TUduTs6bu3EdnSycntVJ4re8kgZA+wx9IueI2Y11bfbgwtzuE0KQ==" - } - } - }, "react": { "version": "18.2.0", "resolved": "https://registry.npmjs.org/react/-/react-18.2.0.tgz", @@ -51208,6 +50707,7 @@ "version": "3.6.0", "resolved": "https://registry.npmjs.org/readable-stream/-/readable-stream-3.6.0.tgz", "integrity": "sha512-BViHy7LKeTz4oNnkcLJ+lVSL6vpiFeX6/d3oSH8zCW7UxP2onchk+vTGB143xuFjHS3deTgkKoXXymXqymiIdA==", + "dev": true, "requires": { "inherits": "^2.0.3", "string_decoder": "^1.1.1", @@ -51668,7 +51168,8 @@ "safe-buffer": { "version": "5.1.2", "resolved": "https://registry.npmjs.org/safe-buffer/-/safe-buffer-5.1.2.tgz", - "integrity": "sha512-Gd2UZBJDkXlY7GbJxfsE8/nvKkUEU1G38c1siN6QP6a9PT9MmHB8GnpscSmMJSoF8LOIrt8ud/wPtojys4G6+g==" + "integrity": "sha512-Gd2UZBJDkXlY7GbJxfsE8/nvKkUEU1G38c1siN6QP6a9PT9MmHB8GnpscSmMJSoF8LOIrt8ud/wPtojys4G6+g==", + "dev": true }, "safe-regex": { "version": "1.1.0", @@ -52120,44 +51621,6 @@ "kind-of": "^6.0.2" } }, - "sharp": { - "version": "0.31.2", - "resolved": "https://registry.npmjs.org/sharp/-/sharp-0.31.2.tgz", - "integrity": "sha512-DUdNVEXgS5A97cTagSLIIp8dUZ/lZtk78iNVZgHdHbx1qnQR7JAHY0BnXnwwH39Iw+VKhO08CTYhIg0p98vQ5Q==", - "requires": { - "color": "^4.2.3", - "detect-libc": "^2.0.1", - "node-addon-api": "^5.0.0", - "prebuild-install": "^7.1.1", - "semver": "^7.3.8", - "simple-get": "^4.0.1", - "tar-fs": "^2.1.1", - "tunnel-agent": "^0.6.0" - }, - "dependencies": { - "lru-cache": { - "version": "6.0.0", - "resolved": "https://registry.npmjs.org/lru-cache/-/lru-cache-6.0.0.tgz", - "integrity": "sha512-Jo6dJ04CmSjuznwJSS3pUeWmd/H0ffTlkXXgwZi+eq1UCmqQwCh+eLsYOYCwY991i2Fah4h1BEMCx4qThGbsiA==", - "requires": { - "yallist": "^4.0.0" - } - }, - "semver": { - "version": "7.3.8", - "resolved": "https://registry.npmjs.org/semver/-/semver-7.3.8.tgz", - "integrity": "sha512-NB1ctGL5rlHrPJtFDVIVzTyQylMLu9N9VICA6HSFJo8MCGVTMW6gfpicwKmmK/dAjTOrqu5l63JJOpDSrAis3A==", - "requires": { - "lru-cache": "^6.0.0" - } - }, - "yallist": { - "version": "4.0.0", - "resolved": "https://registry.npmjs.org/yallist/-/yallist-4.0.0.tgz", - "integrity": "sha512-3wdGidZyq5PB084XLES5TpOSRA3wjXAlIWMhum2kRcv/41Sn2emQ0dycQW4uZXLejwKvg6EsvbdlVL+FYEct7A==" - } - } - }, "shebang-command": { "version": "2.0.0", "resolved": "https://registry.npmjs.org/shebang-command/-/shebang-command-2.0.0.tgz", @@ -52187,36 +51650,6 @@ "integrity": "sha512-wnD2ZE+l+SPC/uoS0vXeE9L1+0wuaMqKlfz9AMUo38JsyLSBWSFcHR1Rri62LZc12vLr1gb3jl7iwQhgwpAbGQ==", "dev": true }, - "simple-concat": { - "version": "1.0.1", - "resolved": "https://registry.npmjs.org/simple-concat/-/simple-concat-1.0.1.tgz", - "integrity": "sha512-cSFtAPtRhljv69IK0hTVZQ+OfE9nePi/rtJmw5UjHeVyVroEqJXP1sFztKUy1qU+xvz3u/sfYJLa947b7nAN2Q==" - }, - "simple-get": { - "version": "4.0.1", - "resolved": "https://registry.npmjs.org/simple-get/-/simple-get-4.0.1.tgz", - "integrity": "sha512-brv7p5WgH0jmQJr1ZDDfKDOSeWWg+OVypG99A/5vYGPqJ6pxiaHLy8nxtFjBA7oMa01ebA9gfh1uMCFqOuXxvA==", - "requires": { - "decompress-response": "^6.0.0", - "once": "^1.3.1", - "simple-concat": "^1.0.0" - } - }, - "simple-swizzle": { - "version": "0.2.2", - "resolved": "https://registry.npmjs.org/simple-swizzle/-/simple-swizzle-0.2.2.tgz", - "integrity": "sha512-JA//kQgZtbuY83m+xT+tXJkmJncGMTFT+C+g2h2R9uxkYIrE2yy9sgmcLhCnw57/WSD+Eh3J97FPEDFnbXnDUg==", - "requires": { - "is-arrayish": "^0.3.1" - }, - "dependencies": { - "is-arrayish": { - "version": "0.3.2", - "resolved": "https://registry.npmjs.org/is-arrayish/-/is-arrayish-0.3.2.tgz", - "integrity": "sha512-eVRqCvVlZbuw3GrM63ovNSNAeA1K16kaR/LRY/92w0zxQ5/1YzwblUX652i4Xs9RwAGjW9d9y6X88t8OaAJfWQ==" - } - } - }, "sisteransi": { "version": "1.0.5", "resolved": "https://registry.npmjs.org/sisteransi/-/sisteransi-1.0.5.tgz", @@ -52786,6 +52219,7 @@ "version": "1.3.0", "resolved": "https://registry.npmjs.org/string_decoder/-/string_decoder-1.3.0.tgz", "integrity": "sha512-hkRX8U1WjJFd8LsDJ2yQ/wWWxaopEsABU1XfkM8A+j0+85JAGppt16cr1Whg6KIbb4okU6Mql6BOj+uup/wKeA==", + "dev": true, "requires": { "safe-buffer": "~5.2.0" }, @@ -52793,7 +52227,8 @@ "safe-buffer": { "version": "5.2.1", "resolved": "https://registry.npmjs.org/safe-buffer/-/safe-buffer-5.2.1.tgz", - "integrity": "sha512-rp3So07KcdmmKbGvgaNxQSJr7bGVSVk5S9Eq1F+ppbRo70+YeaDxkw5Dd8NPN+GD6bjnYm2VuPuCXmpuYvmCXQ==" + "integrity": "sha512-rp3So07KcdmmKbGvgaNxQSJr7bGVSVk5S9Eq1F+ppbRo70+YeaDxkw5Dd8NPN+GD6bjnYm2VuPuCXmpuYvmCXQ==", + "dev": true } } }, @@ -53103,29 +52538,6 @@ } } }, - "tar-fs": { - "version": "2.1.1", - "resolved": "https://registry.npmjs.org/tar-fs/-/tar-fs-2.1.1.tgz", - "integrity": "sha512-V0r2Y9scmbDRLCNex/+hYzvp/zyYjvFbHPNgVTKfQvVrb6guiE/fxP+XblDNR011utopbkex2nM4dHNV6GDsng==", - "requires": { - "chownr": "^1.1.1", - "mkdirp-classic": "^0.5.2", - "pump": "^3.0.0", - "tar-stream": "^2.1.4" - } - }, - "tar-stream": { - "version": "2.2.0", - "resolved": "https://registry.npmjs.org/tar-stream/-/tar-stream-2.2.0.tgz", - "integrity": "sha512-ujeqbceABgwMZxEJnk2HDY2DlnUZ+9oEcb1KzTVfYHio0UE6dG71n60d8D2I4qNvleWrrXpmjpt7vZeF1LnMZQ==", - "requires": { - "bl": "^4.0.3", - "end-of-stream": "^1.4.1", - "fs-constants": "^1.0.0", - "inherits": "^2.0.3", - "readable-stream": "^3.1.1" - } - }, "telejson": { "version": "6.0.8", "resolved": "https://registry.npmjs.org/telejson/-/telejson-6.0.8.tgz", @@ -53497,6 +52909,7 @@ "version": "0.6.0", "resolved": "https://registry.npmjs.org/tunnel-agent/-/tunnel-agent-0.6.0.tgz", "integrity": "sha512-McnNiV1l8RYeY8tBgEpuodCC1mLUdbSN+CYBL7kJsJNInOP8UjDDEwdk6Mw60vdLLrr5NHKZhMAOSrR2NZuQ+w==", + "dev": true, "requires": { "safe-buffer": "^5.0.1" } diff --git a/website/package.json b/website/package.json index 7d3b680e..eb85568b 100644 --- a/website/package.json +++ b/website/package.json @@ -50,7 +50,6 @@ "react": "18.2.0", "react-dom": "18.2.0", "react-icons": "^4.7.1", - "sharp": "0.31.2", "swr": "^2.0.0", "tailwindcss": "^3.2.4", "use-debounce": "^9.0.2" diff --git a/website/src/components/CallToAction.tsx b/website/src/components/CallToAction.tsx index ee6827eb..8a07373f 100644 --- a/website/src/components/CallToAction.tsx +++ b/website/src/components/CallToAction.tsx @@ -48,7 +48,7 @@ export function CallToAction() { here:

- +
); } + +const FooterLink = ({ href, label }: { href: string; label: string }) => + useMemo( + () => ( + + {label} + + ), + [href, label] + ); diff --git a/website/src/components/Header/UserMenu.tsx b/website/src/components/Header/UserMenu.tsx index 2e06606c..c5ca92bd 100644 --- a/website/src/components/Header/UserMenu.tsx +++ b/website/src/components/Header/UserMenu.tsx @@ -2,6 +2,7 @@ import { Box, Link, Text, useColorModeValue } from "@chakra-ui/react"; import { Popover } from "@headlessui/react"; import { AnimatePresence, motion } from "framer-motion"; import Image from "next/image"; +import NextLink from "next/link"; import { signOut, useSession } from "next-auth/react"; import React from "react"; import { FiLayout, FiLogOut, FiSettings } from "react-icons/fi"; @@ -77,6 +78,7 @@ export function UserMenu() { {accountOptions.map((item) => ( = NextPage & { getLayout?: (page: React.ReactElement) => React.ReactNode; @@ -28,7 +30,42 @@ export const getTransparentHeaderLayout = (page: React.ReactElement) => ( export const getDashboardLayout = (page: React.ReactElement) => (
- {page} + + {page} + +
+); + +export const getAdminLayout = (page: React.ReactElement) => ( +
+
+ + {page} +
); diff --git a/website/src/components/Messages.tsx b/website/src/components/Messages.tsx index d3d7b3b8..7b69bc50 100644 --- a/website/src/components/Messages.tsx +++ b/website/src/components/Messages.tsx @@ -1,5 +1,6 @@ import { Grid } from "@chakra-ui/react"; import { useColorMode } from "@chakra-ui/react"; +import { useMemo } from "react"; import { FlaggableElement } from "./FlaggableElement"; @@ -8,29 +9,30 @@ export interface Message { is_assistant: boolean; } -const getBgColor = (isAssistant: boolean, colorMode: "light" | "dark") => { - if (colorMode === "light") { - return isAssistant ? "bg-slate-800" : "bg-sky-900"; - } else { - return isAssistant ? "bg-black" : "bg-sky-900"; - } -}; - export const Messages = ({ messages, post_id }: { messages: Message[]; post_id: string }) => { - const { colorMode } = useColorMode(); + const items = messages.map((messageProps: Message, i: number) => { + const { text } = messageProps; - const items = messages.map(({ text, is_assistant }: Message, i: number) => { return ( -
- {text} -
+ ); }); // Maybe also show a legend of the colors? return {items}; }; + +export const MessageView = ({ is_assistant, text }: Message) => { + const { colorMode } = useColorMode(); + + const bgColor = useMemo(() => { + if (colorMode === "light") { + return is_assistant ? "bg-slate-800" : "bg-sky-900"; + } else { + return is_assistant ? "bg-black" : "bg-sky-900"; + } + }, [colorMode, is_assistant]); + + return
{text}
; +}; diff --git a/website/src/components/Messages/MessageTable.tsx b/website/src/components/Messages/MessageTable.tsx index 65f6efb1..95ccc540 100644 --- a/website/src/components/Messages/MessageTable.tsx +++ b/website/src/components/Messages/MessageTable.tsx @@ -1,5 +1,5 @@ -import { Box, CircularProgress, Stack, StackDivider, useColorModeValue } from "@chakra-ui/react"; -import { MessageTableEntry } from "./MessageTableEntry"; +import { Stack, StackDivider } from "@chakra-ui/react"; +import { MessageTableEntry } from "src/components/Messages/MessageTableEntry"; export function MessageTable({ messages }) { return ( diff --git a/website/src/components/Messages/MessageTableEntry.tsx b/website/src/components/Messages/MessageTableEntry.tsx index 2bc17201..9fad7262 100644 --- a/website/src/components/Messages/MessageTableEntry.tsx +++ b/website/src/components/Messages/MessageTableEntry.tsx @@ -1,9 +1,19 @@ -import { Avatar, Box, HStack, LinkBox, useColorModeValue } from "@chakra-ui/react"; +import { Avatar, HStack, LinkBox, useColorModeValue } from "@chakra-ui/react"; import { boolean } from "boolean"; import NextLink from "next/link"; -import { FlaggableElement } from "../FlaggableElement"; +import { FlaggableElement } from "src/components/FlaggableElement"; -export function MessageTableEntry({ item, idx }) { +interface Message { + text: string; + id: string; + is_assistant: boolean; +} +interface MessageTableEntryProps { + item: Message; + idx: number; +} +export function MessageTableEntry(props: MessageTableEntryProps) { + const { item, idx } = props; const bgColor = useColorModeValue(idx % 2 === 0 ? "bg-slate-800" : "bg-black", "bg-sky-900"); return ( diff --git a/website/src/components/Messages/MessageWithChildren.tsx b/website/src/components/Messages/MessageWithChildren.tsx new file mode 100644 index 00000000..c412f996 --- /dev/null +++ b/website/src/components/Messages/MessageWithChildren.tsx @@ -0,0 +1,104 @@ +import { Box, CircularProgress, Flex, HStack, StackDivider, StackProps, Text, TextProps } from "@chakra-ui/react"; +import { boolean } from "boolean"; +import { useState } from "react"; +import { MessageTableEntry } from "src/components/Messages/MessageTableEntry"; +import fetcher from "src/lib/fetcher"; +import useSWR from "swr"; + +const MessageHeaderProps: TextProps = { + align: "center", + fontSize: "xl", + py: "2", +}; + +const MessageStackProps: StackProps = { + spacing: "2", + alignItems: "start", + justifyContent: "center", + divider: , +}; + +interface MessageWithChildrenProps { + id: string; + depth?: number; + maxDepth?: number; + isOnlyChild?: boolean; +} + +export function MessageWithChildren(props: MessageWithChildrenProps) { + const { id, depth, maxDepth, isOnlyChild = true } = props; + + const [message, setMessage] = useState(null); + const [children, setChildren] = useState(null); + + const { isLoading } = useSWR(id ? `/api/messages/${id}` : null, fetcher, { + onSuccess: (data) => { + setMessage(data); + }, + onError: () => { + setMessage(null); + }, + }); + const { isLoading: isLoadingChildren } = useSWR(id ? `/api/messages/${id}/children` : null, fetcher, { + onSuccess: (data) => { + setChildren(data); + }, + onError: () => { + setChildren(null); + }, + }); + + const renderRecursive = maxDepth && ((depth && depth < maxDepth) || !depth); + const isFirst = depth === 0 || !depth; + const isFirstOrOnly = isFirst || boolean(isOnlyChild); + + if (isLoading || isLoadingChildren) { + return ; + } + + return ( + <> + {message && ( + <> + {isFirst ? "Message" : depth === 1 ? "Children" : "Ancestor"} + + + + + + + + + )} + {children && Array.isArray(children) && children.length > 0 ? ( + renderRecursive ? ( + + {children.map((item, idx) => ( + + + + ))} + + ) : ( + <> + {isFirstOrOnly ? "Children" : "Ancestor"} + + {children.map((item, idx) => ( + + + + ))} + + + ) + ) : ( + <> + )} + + ); +} diff --git a/website/src/components/Dashboard/SideMenu.tsx b/website/src/components/SideMenu.tsx similarity index 74% rename from website/src/components/Dashboard/SideMenu.tsx rename to website/src/components/SideMenu.tsx index 499117a2..3722eaa8 100644 --- a/website/src/components/Dashboard/SideMenu.tsx +++ b/website/src/components/SideMenu.tsx @@ -1,37 +1,24 @@ -import { Box, Button, Link, Text, Tooltip, useColorMode } from "@chakra-ui/react"; +import { Box, Button, Text, Tooltip, useColorMode } from "@chakra-ui/react"; +import Link from "next/link"; import { useRouter } from "next/router"; -import { FiLayout, FiSun, FiMessageSquare } from "react-icons/fi"; +import { FiSun } from "react-icons/fi"; +import { IconType } from "react-icons/lib"; import { colors } from "styles/Theme/colors"; -export function SideMenu() { +export interface MenuButtonOption { + label: string; + pathname: string; + desc: string; + icon: IconType; +} + +export interface SideMenuProps { + buttonOptions: MenuButtonOption[]; +} + +export function SideMenu(props: SideMenuProps) { const router = useRouter(); const { colorMode, toggleColorMode } = useColorMode(); - const buttonOptions = [ - { - label: "Dashboard", - pathname: "/dashboard", - desc: "Dashboard Home", - icon: FiLayout, - }, - { - label: "Messages", - pathname: "/messages", - desc: "Messages Dashboard", - icon: FiMessageSquare, - }, - // { - // label: "Leaderboard", - // pathname: "#", - // desc: "Public Leaderboard", - // icon: FiAward, - // }, - // { - // label: "Stats", - // pathname: "#", - // desc: "User Statistics", - // icon: FiBarChart2, - // }, - ]; return (
@@ -43,7 +30,7 @@ export function SideMenu() { className="grid grid-cols-4 gap-2 sm:flex sm:flex-col sm:justify-between p-4 h-full" >